Speech editing has garnered more and more attention due to its diverse applications. However, existing systems often require substantial manual effort or have limited capabilities in attribute editing, imposing significant constraints. In this work, we present SpeechPalette, a comprehensive high-quality speech editing method that allows users to easily modify various attributes of the selected speech segment according to their preferences. Specifically, the proposed model approaches speech editing from a decoupling perspective, disentangling critical information such as text, pitch, duration and more from the input speech. Then, reconstruction is achieved through a mask and prediction mechanism. Furthermore, we leverage a diffusion model to predict the residuals between the real and predicted speech, further enhancing synthesis quality. The proposed method not only excels at text-based speech editing but also handles tasks involving pitch and speed rate adjustments. Moreover, it also demonstrates remarkable performance in one-shot text-to-speech scenarios. While recent large-scale models achieve impressive synthesis quality through massive computational resources, SpeechPalette offers a balanced approach with explicit fine-grained control over speech attributes, practical deployment requirements, and competitive performance relative to similarly-sized systems. Experimental results across a range of tasks consistently demonstrate the superior performance of our method compared to baseline systems. Additionally, comprehensive ablation studies validate the effectiveness of our proposed approach.

The active speaker detection task is to determine whether a person is speaking or not across a series of video frames. Existing methods heavily rely on facial information within the annotated face bounding boxes for cross-modal learning with audio. This leads to a substantial decline in detection performance when facial cues are unclear, such as in cases of face occlusion or low-resolution facial appearances. In this paper, we extend the perception scale using only face bounding box annotations to model both facial and gestural cues, addressing the over-reliance on facial cues in active speaker detection. We propose a novel graph neural network that models inter-speaker interactions and integrates various cues from individual speakers. The final detection results are obtained through a binary graph node classification task. Our method achieves state-of-the-art performance on the AVA-ActiveSpeaker dataset (mAP: 95.6%) and the ASW dataset (mAP: 99.4%), with a model size only 21% that of the second-best method. Additionally, when facial cues are of poor quality, our method demonstrates a significant performance advantage over existing approaches. The code and model weights will be available athttps://github.com/sdqdlgj/MSSG.

Code-switching is a linguistic phenomenon in which different languages are used interactively during conversation. It poses significant performance challenges to natural language processing (NLP) tasks due to the often monolingual nature of the underlying system. We focus on sentence-level semantic associations between the different code-switching expressions. And we propose an innovative task-free semantic learning method based on the semantic property. Specifically, there are many different ways of languages switching for a sentence with the same meaning. We refine this into a semantic computational method by designing the loss of semantic invariant constraint during the model optimization. In this work, we conduct thorough experiments on speech recognition, speech translation, and language modeling tasks. The experimental results fully demonstrate that the proposed method can widely improve the performance of code-switching related tasks.

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive optimization ensures an appropriate trade-off between memory stability and learning plasticity. Additionally, to address the increase of redundant neurons from old tasks, we further introduce the Ebbinghaus forgetting mechanism to release them, thereby promoting the model’s ability to learn more generalized discriminative features. Experimental results show our method achieves a 21.3 percent improvement in EER over the state-of-the-art continual learning approach RWM for audio deepfake detection. Moreover, the effectiveness of RegO extends beyond the audio deepfake detection domain, showing potential significance in other tasks, such as image recognition.

Partially deepfake audio attacks have attracted the attention recently, and the demand for locating the manipulation regions of partially deepfake audio arises accordingly. However, existing methods are usually proposed based on frame-level authenticity detection or splicing boundaries detection, neglecting the temporal self-consistency of audio. In this paper, we propose a novel method for partially deepfake audio localization based on temporal self-consistency learning via high-frequency components, named as PET. The results demonstrates that, in ADD 2023 Track 2 eval set, it could achieve the segment F1-score at 0.7397 without any data augmentation strategies, which is 21.94% higher than that of the system ranked 1st on the leaderboard. It also confirms the effectiveness and well generalization ability of PET.

Partially deepfake audio localization is important in audio forensics. However, existing localization models for partially deepfake audio face two major challenges: distribution shifts between training and testing data as well as insufficient utilization of information from both manipulated regions and boundaries. To address these challenges, we propose to use Adversarial training and Gradient Optimization (AGO) to improve partially fake audio localization. Specifically, we apply a gradient reversal layer to reduce the dependence on domain-specific features, enhancing the model’s generalization ability. Additionally, we introduce an alternating update strategy to learn information from both manipulated regions and boundaries, while orthogonal gradient updates minimize conflicts between the two tasks. We evaluated AGO on both the ADD2023 track 2 and PartialSpoof datasets. We achieved a 22.82% relative improvement over the first-ranked method of the ADD2023 track 2. We also achieved state-of-the-art results on the PartialSpoof dataset. Our code is available at https://github.com/Little-dingding/ATGO.

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and watermark embedding-extraction in an end-to-end manner, optimizing both imperceptibility and extractability of the watermark. Furthermore, We design an iterative Attention Imprint Unit (AIU) for deeper feature integration of watermark and speech, reducing the impact of quantization noise on the watermark. Experimental results show WMCodec outperforms AudioSeal with Encodec in most quality metrics for watermark imperceptibility and consistently exceeds both AudioSeal with Encodec and reinforced TraceableSpeech in extraction accuracy of watermark. At bandwidth of 6 kbps with a watermark capacity of 16 bps, WMCodec maintains over 99% extraction accuracy under common attacks, demonstrating strong robustness.

The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level—from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suffers from a lack of large-scale datasets with intensive, descriptive emotion annotations, as well as a multimodal-centric framework to maximize the potential of MLLMs for emotion understanding. To address this, we establish a new benchmark for MLLM-based emotion understanding with a novel dataset (MER-Caption) and a new model (AffectGPT). Utilizing our model-based crowd-sourcing data collection strategy, we construct the largest descriptive emotion dataset to date (by far), featuring over 2K fine-grained emotion categories across 115K samples. We also introduce the AffectGPT model, designed with pre-fusion operations to enhance multimodal integration. Finally, we present MER-UniBench, a unified benchmark with evaluation metrics tailored for typical MER tasks and the free-form, natural language output style of MLLMs. Extensive experimental results show AffectGPT's robust performance across various MER tasks. We have released both the code and the dataset to advance research and development in emotion understanding: https://github.com/zeroQiaoba/AffectGPT.

Multimodal Emotion Recognition (MER) is a critical research area that seeks to decode human emotions from diverse data modalities. However, existing machine learning methods predominantly rely on predefined emotion taxonomies, which fail to capture the inherent complexity, subtlety, and multi-appraisal nature of human emotional experiences, as demonstrated by studies in psychology and cognitive science. To overcome this limitation, we advocate for introducing the concept of open vocabulary into MER. This paradigm shift aims to enable models to predict emotions beyond a fixed label space, accommodating a flexible set of categories to better reflect the nuanced spectrum of human emotions. To achieve this, we propose a novel paradigm: Open-Vocabulary MER (OV-MER), which enables emotion prediction without being confined to predefined spaces. However, constructing a dataset that encompasses the full range of emotions for OV-MER is practically infeasible; hence, we present a comprehensive solution including a newly curated database, novel evaluation metrics, and a preliminary benchmark. By advancing MER from basic emotions to more nuanced and diverse emotional states, we hope this work can inspire the next generation of MER, enhancing its generalizability and applicability in real-world scenarios. Code and dataset are available at: https://github.com/zeroQiaoba/AffectGPT.

Audio deepfake detection (ADD) has grown increasingly important due to the rise of high-fidelity audio generative models and their potential for misuse. Given that audio large language models (ALLMs) have made significant progress in various audio processing tasks, a heuristic question arises: Can ALLMs be leveraged to solve ADD?. In this paper, we first conduct a comprehensive zero-shot evaluation of ALLMs on ADD, revealing their ineffectiveness. To this end, we propose ALLM4ADD, an ALLM-driven framework for ADD. Specifically, we reformulate ADD task as an audio question answering problem, prompting the model with the question: ''Is this audio fake or real?''. We then perform supervised fine-tuning to enable the ALLM to assess the authenticity of query audio. Extensive experiments are conducted to demonstrate that our ALLM-based method can achieve superior performance in fake audio detection, particularly in data-scarce scenarios. As a pioneering study, we anticipate that this work will inspire the research community to leverage ALLMs to develop more effective ADD systems. Code is available at https://github.com/ucas-hao/qwen_audio_for_add.git.

The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition.

Pre-trained Language Models (PLMs) like BERT have achieved superior performance on different downstream tasks, even when such a model is trained on a general domain. Moreover, recent studies have shown that continued pre-training on task-specific data, known as task adaptive pre-training (TAPT), can further improve downstream task performance. However, conventional TAPT adjusts all the parameters of the PLMs, which distorts the learned generic knowledge embedded in the original PLMs weights, and it is expensive to store a whole model copy for each downstream task. In this paper, we propose NLoPT, a two-step n-gram enhanced low-rank task adaptive pre-training method, to effectively and efficiently customize a PLM to the downstream task. Specifically, we first apply low-rank adaption (LoRA), a prevalent parameter-efficient technique, for efficient TAPT. We further explicitly incorporate the task-specific multi-granularity n-gram information via the cross-attention mechanism. Experimental results on six datasets from four domains illustrate the effectiveness of NLoPT, demonstrating the superiority of LoRA based TAPT and the necessity of incorporating task-specific n-gram information.

Language model based text-to-speech (TTS) models, like VALL-E, have gained attention for their outstanding in-context learning capability in zero-shot scenarios. Neural speech codec is a critical component of these models, which can convert speech into discrete token representations. However, excessive token sequences from the codec may negatively affect prediction accuracy and restrict the progression of Language model based TTS models. To address this issue, this paper proposes a novel neural speech codec with time-invariant codes named TiCodec. By encoding and quantizing time-invariant information into a separate code, TiCodec can reduce the amount of frame-level information that needs encoding, effectively decreasing the number of tokens as codes of speech. Furthermore, this paper introduces a time-invariant encoding consistency loss to enhance the consistency of time-invariant code within an utterance, which can benefit the zero-shot TTS task. Experimental results demonstrate that TiCodec can not only enhance the quality of reconstruction speech with fewer tokens but also increase the similarity and naturalness, as well as reduce the word error rate of the synthesized speech by the TTS model. The code is publicly available at https://github.com/y-ren16/TiCodec.

With the widespread application of Automatic Speaker Verification (ASV) technology in security authentication, the threat of fake audio attacks looms as a malicious means compromising system security. In this study, we employ the multi-scale permutation entropy (MPE) in audio deepfake detection, which could help measure the complexity and detect the dynamic characteristics of audio signals at different scales. Experimental results indicate that MPE can effectively improve the performance of LFCC. For example, on the ASVspoof2019 LA test set, it successfully achieves an equal error rate (EER) of less than 2%, which is around 50% lower than that of LFCC. Notably, MPE exhibits extraordinary generalization performance when applied to the In-the-Wild dataset, as its performance of EER is comparable to that of Wav2vec, without requiring pretraining. Therefore, we believe that MPE holds promising prospects in voice biometric recognition for anti-spoofing applications. Our code is available at https://github.com/ADDchallenge/MPE-for-audio-deepfake-detection

Fake artefacts for discriminating between bonafide and fake audio can exist in both short-and long-range segments.Therefore, combining local and global feature information can effectively discriminate between bonafide and fake audio.This paper proposes an end-to-end bidirectional state space model, named RawBMamba, to capture both short-and long-range discriminative information for audio deepfake detection.Specifically, we use sinc Layer and multiple convolutional layers to capture short-range features, and then design a bidirectional Mamba to address Mamba's unidirectional modelling problem and further capture long-range feature information.Moreover, we develop a bidirectional fusion module to integrate embeddings, enhancing audio context representation and combining shortand long-range information.The results show that our proposed RawBMamba achieves a 34.1% improvement over Rawformer on ATSVspoof2021 LA dataset, and demonstrates competitive performance on other datasets.Codes will be released on https://github.com/cyjie429/RawBMamba.

International audience

Speaker extraction aims to selectively extract the target speaker from the multi-talker environment under the guidance of auxiliary reference. Recent studies have shown that the attended speaker's information can be decoded by the auditory attention decoding from the listener's brain activity. However, how to more effectively utilize the common information about the target speaker contained in both electroencephalography (EEG) and speech is still an unresolved problem. In this paper, we propose a multi-scale fusion network (MSFNet) for brain-controlled speaker extraction, which utilizes the EEG recorded from the listener to extract the target speech. In order to make full use of the speech information, the mixed speech is encoded with multiple time scales so that the multi-scale embeddings are acquired. In addition, to effectively extract the non-Euclidean data of EEG, the graph convolutional networks are used as the EEG encoder. Finally, these multi-scale embeddings are separately fused with the EEG features. To facilitate research related to auditory attention decoding and further validate the effectiveness of the proposed method, we also construct the AVED dataset, a new EEG-Audio dataset. Experimental results on both the public Cocktail Party dataset and the newly proposed AVED dataset in this paper show that our MSFNet model significantly outperforms the state-of-the-art method in certain objective evaluation metrics.

Fake audio detection is an emerging active topic. A growing number of literatures have aimed to detect fake utterance, which are mostly generated by Text-to-speech (TTS) or voice conversion (VC). However, countermeasures against impersonation remain an underexplored area. Impersonation is a fake type that involves an imitator replicating specific traits and speech style of a target speaker. Unlike TTS and VC, which often leave digital traces or signal artifacts, impersonation involves live human beings producing entirely natural speech, rendering the detection of impersonation audio a challenging task. Thus, we propose a novel method that integrates speaker profiles into the process of impersonation audio detection. Speaker profiles are inherent characteristics that are challenging for impersonators to mimic accurately, such as speaker's age, job. We aim to leverage these features to extract discriminative information for detecting impersonation audio. Moreover, there is no large impersonated speech corpora available for quantitative study of impersonation impacts. To address this gap, we further design the first large-scale, diverse-speaker Chinese impersonation dataset, named ImPersonation Audio Detection (IPAD), to advance the community's research on impersonation audio detection. We evaluate several existing fake audio detection methods on our proposed dataset IPAD, demonstrating its necessity and the challenges. Additionally, our findings reveal that incorporating speaker profiles can significantly enhance the model's performance in detecting impersonation audio.

In recent years, fake audio detection (FAD) has made great progress, and lightweight is important to achieve fast and reliable audio authenticity verification on resource-limited devices. However, most of the researchers ignore lightweight when improving the performance of FAD. To develop the application of FAD for small-end devices, this paper proposes a novel light-weight network named Light-ECA2Net. Given that networks with different depths have different abilities in capturing fake speech artifacts, this paper proposes a dynamic ensemble teacher-student distillation framework to fully transfer distillation knowledge. The dynamic ensemble distillation is divided into two aspects. First, we adopt one-to-one feature mapping to perceive the multidimensional feature knowledge and dynamically adjust every dimension feature weight by using ground truth labels, which can enable students to receive feature knowledge efficiently. Secondly, different network layers also have their strengths of predicting, further dynamically predicting weight can improve the learning ability of the student. Experimental results on the ASVspoof 2019 LA and PA datasets show that compared to the baseline, our system further improves performance by reducing the model complexity by 45%.

Most research in synthetic speech detection (SSD) focuses on improving performance on standard noise-free datasets. However, in actual situations, noise interference is usually present, causing significant performance degradation in SSD systems. To improve noise robustness, this paper proposes a dual-branch knowledge distillation synthetic speech detection (DKDSSD) method. Specifically, a parallel data flow of the clean teacher branch and the noisy student branch is designed, and interactive fusion module and response-based teacher-student paradigms are proposed to guide the training of noisy data from both the data distribution and decision-making perspectives. In the noisy student branch, speech enhancement is introduced initially for denoising, aiming to reduce the interference of strong noise. The proposed interactive fusion combines denoised features and noisy features to mitigate the impact of speech distortion and ensure consistency with the data distribution of the clean branch. The teacher-student paradigm maps the student's decision space to the teacher's decision space, enabling noisy speech to behave similarly to clean speech. Additionally, a joint training method is employed to optimize both branches for achieving global optimality. Experimental results based on multiple datasets demonstrate that the proposed method performs effectively in noisy environments and maintains its performance in cross-dataset experiments. Source code is available athttps://github.com/fchest/DKDSSD.

Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.

In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very important, such as spectrogram defects, mute segments, and so on, which are often perceived by shallow networks. However, shallow networks have much noise, which can not capture this very well. To address this problem, we propose using the deepest network instruct shallow network for enhancing shallow networks. Specifically, the networks of FSD are divided into several segments, the deepest network being used as the teacher model, and all shallow networks become multiple student models by adding classifiers. Meanwhile, the distillation path between the deepest network feature and shallow network features is used to reduce the feature difference. A series of experimental results on the ASVspoof 2019 LA and PA datasets show the effectiveness of the proposed method, with significant improvements compared to the baseline.

Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset. The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets. To overcome this limitation, we propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting, called Regularized Adaptive Weight Modification (RAWM). When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. The adaptive modification direction ensures the network can effectively detect fake audio on the new dataset while preserving its knowledge of old model, thus mitigating catastrophic forgetting. In addition, genuine audio collected from quite different acoustic conditions may skew their feature distribution, so we introduce a regularization constraint to force the network to remember the old distribution in this regard. Our method can easily be generalized to related fields, like speech emotion recognition. We also evaluate our approach across multiple datasets and obtain a significant performance improvement on cross-dataset experiments.

The first Multimodal Emotion Recognition Challenge (MER 2023)1 was successfully held at ACM Multimedia. The challenge focuses on system robustness and consists of three distinct tracks: (1) MER-MULTI, where participants are required to recognize both discrete and dimensional emotions; (2) MER-NOISE, in which noise is added to test videos for modality robustness evaluation; (3) MER-SEMI, which provides a large amount of unlabeled samples for semi-supervised learning. In this paper, we introduce the motivation behind this challenge, describe the benchmark dataset, and provide some statistics about participants. To continue using this dataset after MER 2023, please sign a new End User License Agreement2 and send it to our official email address3. We believe this high-quality dataset can become a new benchmark in multimodal emotion recognition, especially for the Chinese research community.

Prosodic boundaries are still crucial to the naturalness of end-to-end speech synthesis systems. This article proposes to use adversarial multi-task learning to predict prosodic boundaries. Adversarial multi-task learning is utilized to transfer knowledge from an auxiliary POS tagging task to a prosodic boundary prediction task. Furthermore, multi-modal embeddings are composed of contextual word and speech embedding features obtained from the pre-trained bidirectional encoder representations from transformers (BERT) model and Speech2Vec. We can utilize linguistic and acoustic information from large amounts of external text and speech data without prosodic boundary labels. At the inference stage, the prosodic boundary predicting model can use the syntactic features learnt from the POS tagging task without any extra computation cost due to only employing the prosodic boundary predicting task to decode. We conducted experiments on Mandarin datasets. The results show that the models using multi-modal embeddings from the pre-trained BERT and Speech2Vec outperform the models trained with single modal embedding. Furthermore, the models trained with adversarial training obtain further performance gains by up to 2.95% in$F_{1}$score.

The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural and it is not obvious how to synthesize records according to a new word not appearing in the transcript. This paper proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet), which avoids the unnatural phenomenon caused by cut-copy-paste operation in the traditional method and can synthesize a new word not appearing in the transcript. Besides, three text-based speech editing operations based on CampNet are designed: deletion, replacement, and insertion. These operations can comprehensively cover different kinds of situations that text-based speech editing can face. The subjective and objective experiments on VCTK and LibriTTS data sets show that the speech editing results based on CampNet are better than TTS technology, manual editing, and VoCo method (the combination of speech synthesis and speech conversion). We also conducted detailed ablation experiments to explore the effect of the CampNet structure on its performance. Examples of generated speech can be found at https://hairuo55.github.io/CampNet-demo.

Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.

There are many methods for detecting forged audio produced by conversion and synthesis. However, as a simpler method of forgery, splicing has not attracted widespread attention. Based on the characteristic that the tampering operation will cause singularities at high-frequency components, we propose a high-frequency singularity detection feature obtained by wavelet transform. The proposed feature can explicitly show the location of the tampering operation on the waveform. Moreover, the long short-term memory (LSTM) is introduced to the CNN-architecture LCNN to ensure that the sequence information can be fully learned. The proposed feature is sent to the improved RNN-architecture LCNN together with the widely used linear frequency cepstral coefficients (LFCC) to learn forgery characteristics where the LFCC is used as a supplement. Systematic evaluation and comparison show that the proposed method has greatly improved the accuracy and generalization.

Over the last few years, the technology of speech synthesis and voice conversion has made significant improvement with the development of deep learning. The models can generate realistic and human-like speech. It is difficult for most people to distinguish the generated audio from the real. However, this technology also poses a great threat to the global political economy and social stability if some attackers and criminals misuse it with the intent to cause harm. In this workshop, we aim to bring together researchers from the fields of audio deepfake detection, audio deep synthesis, audio fake game and adversarial attacks to further discuss recent research and future directions for detecting deepfake and manipulated audios in multimedia.

The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in one inference step. However, the NAR model still faces two major problems. Firstly, there is still a great gap in performance between the NAR models and the advanced AR models. Secondly, it’s difficult for most of the NAR models to train and converge. We propose a hybrid autoregressive and non-autoregressive transformer (HANAT) model, which integrates AR and NAR models deeply by sharing parameters. We assume that the AR model will assist the NAR model to learn some linguistic dependencies and accelerate the convergence. Furthermore, the two-stage hybrid inference is applied to improve the model performance. All the experiments are conducted on a mandarin dataset ASIEHLL-1 and a english dataset librispeech-960 h. The results show that the HANAT can achieve a competitive performance with the AR model and outperform many complicated NAR models. Besides, the RTF is only 1/5 of the AR model.

The traditional vocoders have the advantages of high synthesis efficiency, strong interpretability, and speech editability, while the neural vocoders have the advantage of high synthesis quality. To combine the advantages of two vocoders, inspired by the traditional deterministic plus stochastic model, this paper proposes a novel neural vocoder named NeuralDPS which can retain high speech quality and acquire high synthesis efficiency and noise controllability. Firstly, this framework contains four modules: a deterministic source module, a stochastic source module, a neural V/UV decision module and a neural filter module. The input required by the vocoder is just the spectral parameter, which avoids the error caused by estimating additional parameters, such as F0. Secondly, to solve the problem that different frequency bands may have different proportions of deterministic components and stochastic components, a multiband excitation strategy is used to generate a more accurate excitation signal and reduce the neural filter’s burden. Thirdly, a method to control noise components of speech is proposed. In this way, the signal-to-noise ratio (SNR) of speech can be adjusted easily. Objective and subjective experimental results show that our proposed NeuralDPS vocoder can obtain similar performance with the WaveNet and it generates waveforms at least 280 times faster than the WaveNet vocoder. It is also 28% faster than WaveGAN’s synthesis efficiency on a single CPU core. We have also verified through experiments that this method can effectively control the noise components in the predicted speech and adjust the SNR of speech.

The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural due to cut-copy-paste operation. In addition, it is not obvious how to synthesize records according to a new word not appearing in the transcript, which often needs the help of text-to-speech (TTS) and voice conversion (VC) technology at the same time. This paper first proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet). The model can simulate the text-based speech editing process by randomly masking part of speech and then predicting the masked region by sensing the speech context. It can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript. Secondly, for the possible operation of text-based speech editing, we design three text-based operations based on CampNet: deletion, insertion, and replacement. These operations can cover various situations of speech editing. Thirdly, to synthesize the speech corresponding to long text in insertion and replacement operations, a word-level autoregressive generation method is proposed, which can synthesize the speech of arbitrary length text. Fourthly, we propose a speaker adaptation method using only one sentence for CampNet and explore the ability of few-shot learning based on CampNet, which provides a new idea for speech forgery tasks. The subjective and objective experiments11Examples of generated speech can be found athttps://hairuo55.github.io/CampNet.on VCTK and LibriTTS datasets show that the speech editing results based on CampNet are better than TTS technology, manual editing, and VoCo method (the combination of TTS and VC). We also conduct detailed ablation experiments to explore the effect of the CampNet structure on its performance. Finally, the experiment shows that speaker adaptation with only one sentence can further improve the naturalness of speech editing for one-shot learning.

Despite the recent significant advances witnessed in end-to-end (E2E) ASR system for code-switching, hunger for audio-text paired data limits the further improvement of the models’ performance. In this paper, we propose a decoupled transformer model to use mono-lingual paired data and unpaired text data to alleviate the problem of code-switching data shortage. The model is decoupled into two parts: audio-to-phoneme (A2P) network and phoneme-to-text (P2T) network. The A2P network can learn acoustic pattern scenarios using large-scale monolingual paired data. Meanwhile, it generates multiple phoneme sequence candidates for single audio data in real time during the training process. Then the generated phoneme-text paired data is used to train the P2T network. This network can be pre-trained with large amounts of external unpaired text data. By using monolingual data and unpaired text data, the decoupled transformer model reduces the high dependency on code-switching paired training data of E2E model to a certain extent. Finally, the two networks are optimized jointly through attention fusion. We evaluate the proposed method on the public Mandarin-English code-switching dataset. Compared with our transformer baseline, the proposed method achieves 18.14% relative mix error rate reduction.

End-to-end framework can generate high-quality and high-similarity speech in the personalized speech synthesis task. However, the generalization of out-of-domain texts is still a challenging task. Limited target data leads to unacceptable errors and poor prosody and similarity performance of the synthetic speech. In this paper, we present a bi-level function decoupling framework to realise separate modeling and controlling for solving above problems. Firstly, on the style representation modeling level, compared with the conventional methods that use single embedding to model all the text dependent discrepancies, it is proposed that the speaker embedding and prosody embedding are modeled separately based on the reference audio and phonetic posteriorgram (PPG) by a multi-head attention mechanism. Secondly, on the model structure level, the decoder model structure is factored into average-net and adaptation-net, where the duration prosody controlling and speaker timbre imitation are mainly designed in relatively separate areas. Experimental results on Mandarin dataset show that the proposed methods lead to an improvement on both robustness, naturalness and similarity.

The paper describes the CASIA speech synthesis system entry for challenge M2VoC 2021. The low similarity and naturalness of synthesized speech remains a challenging problem for speaker adaptation with few resources. Since the end-to-end acoustic model is too complex to interpret, overfitting will occur when training with few data. To prevent the model from overfitting, this paper proposes a novel speaker adaptation framework that decomposes the prosody and voice characteristics in the end-to-end model. A prosody control attention is proposed to control the phonemes’ duration of different speakers. To make the attention controlled by the prosody information, a set of phoneme-level transition tokens is auto-learned from the prosody encoder in our framework and these transition tokens can determine the duration of phonemes in the attention mechanism. Secondly, when we need to use small data set for speaker adaptation, we just need to adapt the speaker related prosody model and decoder, which can prevent the model from overfitting. Further, we use a data puring model to automatically optimize the quality of datasets. Experiments demonstrate the effectiveness of speaker adaptation based on our method, and we (team identifier is T03) get the top three results in competition M2VoC by using this framework.

Aiming at efficiently predicting acoustic features with high naturalness and robustness, this paper proposes PATNet, a neural acoustic model for speech synthesis using phoneme-level autoregression. PATNet accepts phoneme sequences as input and is built based on Transformer structure. PATNet adopts a duration model instead of attention mechanism for sequence alignment. The decoder of PATNet predicts multi-frame spectra within one phoneme in parallel given the predicted spectra of previous phonemes. Such phoneme-level autoregression enables PATNet to achieve higher inference efficiency than the models with frame-level autoregression, such as Transformer-TTS, and improves the robustness of acoustic feature prediction by utilizing phoneme boundaries explicitly. Experimental results show that the speech synthesized by PATNet obtained lower character error rate (CER) than Tacotron, Transfomer-TTS and FastSpeech when evaluated by a speech recognition engine. Besides, PATNet achieved 10 times faster inference speed than Transformer-TTS and significantly better naturalness than FastSpeech.

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data. Fine-tuning and retraining from scratch have been applied to incorporate new data. However, fine-tuning leads to performance degradation on previous data. Retraining takes a lot of time and computation resources. Besides, previous data are unavailable due to privacy in some situations. To solve the above problems, this paper proposes detecting fake without forgetting, a continual-learning-based method, to make the model learn new spoofing attacks incrementally. A knowledge distillation loss is introduced to loss function to preserve the memory of original model. Supposing the distribution of genuine voice is consistent among different scenarios, an extra embedding similarity loss is used as another constraint to further do a positive sample alignment. Experiments are conducted on the ASVspoof2019 dataset. The results show that our proposed method outperforms fine-tuning by the relative reduction of average equal error rate up to 81.62%.

Transducer-based models, such as RNN-Transducer and transformer-transducer, have achieved great success in speech recognition. A typical transducer model decodes the output sequence conditioned on the current acoustic state and previously predicted tokens step by step. Statistically, The number of blank tokens in the prediction results accounts for nearly 90\% of all tokens. It takes a lot of computation and time to predict the blank tokens, but only the non-blank tokens will appear in the final output sequence. Therefore, we propose a method named fast-skip regularization, which tries to align the blank position predicted by a transducer with that predicted by a CTC model. During the inference, the transducer model can predict the blank tokens in advance by a simple CTC project layer without many complicated forward calculations of the transducer decoder and then skip them, which will reduce the computation and improve the inference speed greatly. All experiments are conducted on a public Chinese mandarin dataset AISHELL-1. The results show that the fast-skip regularization can indeed help the transducer model learn the blank position alignments. Besides, the inference with fast-skip can be speeded up nearly 4 times with only a little performance degradation.

Diverse promising datasets have been designed to further the development of fake audio detection, such as ASVspoof databases.However, previous datasets ignore an attacking situation, in which the hacker hides some small fake clips in real speech audio.This poses a serious threat since that it is difficult to distinguish the small fake clip from the whole speech utterance.Therefore, this paper develops such a dataset for half-truth audio detection (HAD).Partially fake audio in the HAD dataset involves only changing a few words in an utterance.The audio of the words is generated with the very latest state-of-the-art speech synthesis technology.We can not only detect fake uttrances but also localize manipulated regions in a speech using this dataset.Some benchmark results are presented on this dataset.The results show that partially fake audio presents much more challenging than fully fake audio for fake audio detection.The HAD dataset is publicly available 1 .

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because the decoder predicts text tokens (such as characters or words) in an autoregressive manner, it is difficult for an AED model to predict all tokens in parallel. This makes the inference speed relatively slow. In contrast, we propose an end-to-end non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once). The model aggregates encoded speech features into the hidden representations corresponding to each token with attention mechanisms. Thus, the model can capture the token relations by self-attention on the aggregated hidden representations from the whole speech signal rather than autoregressive modeling on tokens. Without explicitly autoregressive language modeling, this model predicts all tokens in the sequence in parallel so that the inference is efficient. Moreover, we propose a cross-modal transfer learning method to use a text-modal language model to improve the performance of speech-modal LASO by aligning token semantics. We conduct experiments on two scales of public Chinese speech datasets AISHELL-1 and AISHELL-2. Experimental results show that our proposed model achieves a speedup of about 50× and competitive performance, compared with the autoregressive transformer models. And the cross-modal knowledge transferring from the text-modal model can improve the performance of the speech-modal model.

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It is challenging to incorporate external text-only data into AED models. Another issue of the AED model is that it does not use the right context of a text token while predicting the token. To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence. The method is divided into two stages. First, in the representation stage, a language model is trained on the text. It can be seen as that the knowledge in the text is compressed into the LM. Then, at the transferring stage, the knowledge is transferred to the AED model via teacher-student learning. To further use the whole context of the text sentence, we propose an LM called causal cloze completer (COR), which estimates the probability of a token, given both the left context and the right context of it. Therefore, with LST training, the AED model can leverage the whole context in the sentence. Different from fusion based methods, which use LM during decoding, the proposed method does not increase any extra complexity at the inference stage. We conduct experiments on two scales of public Chinese datasets AISHELL-1 and AISHELL-2. The experimental results demonstrate the effectiveness of leveraging external text-only data and the whole context in a sentence with our proposed method, compared with baseline hybrid systems and AED model based systems.

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the input of the speech recognition component, which are affected by the speech distortion problem. In order to address this problem, this paper proposes a gated recurrent fusion (GRF) method with joint training framework for robust end-to-end ASR. The GRF algorithm is used to dynamically combine the noisy and enhanced features. Therefore, the GRF can not only remove the noise signals from the enhanced features, but also learn the raw fine structures from the noisy features so that it can alleviate the speech distortion. The proposed method consists of speech enhancement, GRF and speech recognition. Firstly, the mask based speech enhancement network is applied to enhance the input speech. Secondly, the GRF is applied to address the speech distortion problem. Thirdly, to improve the performance of ASR, the state-of-the-art speech transformer algorithm is used as the speech recognition component. Finally, the joint training framework is utilized to optimize these three components, simultaneously. Our experiments are conducted on an open-source Mandarin speech corpus called AISHELL-1. Experimental results show that the proposed method achieves the relative character error rate (CER) reduction of 10.04% over the conventional joint enhancement and transformer method only using the enhanced features. Especially for the low signal-to-noise ratio (0 dB), our proposed method can achieves better performances with 12.67% CER reduction, which suggests the potential of our proposed method.

End-to-end speech synthesis can generate high-quality synthetic speech and achieve high similarity scores with low-resource adaptation data. However, the generalization of out-domain texts is still a challenging task. The limited adaptation data leads to unacceptable errors and the poor prosody performance of the synthetic speech. In this paper, we present two novel methods to handle the above problems by focusing on the attention. Firstly, compared with the conventional methods that extract prosody embeddings for conditioning input, a duration controller with feedback mechanism is proposed, which can control the states transition in the sequence-to-sequence model more directly and precisely. Secondly, to alleviate the unmatching text-audio pairs' impact on model, an adaptative optimization strategy which would consider the matching degree of the training sample is also proposed. Experimental results on Mandarin dataset show that proposed methods lead to an improvement on both robustness and overall naturalness.

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these models difficult to be applied for online speech recognition. In this paper, we propose a model named synchronous transformer to address this problem, which can predict the output sequence chunk by chunk. Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately. During training, a forward-backward algorithm is introduced to optimize all the possible alignment paths. Our model is evaluated on a Mandarin dataset AISHELL-1. The experiments show that the synchronous transformer is able to perform encoding and decoding synchronously, and achieves a character error rate of 8.91% on the test set.

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications.To address this issue, we propose a non-autoregressive end-to-end speech recognition system called LASO (listen attentively, and spell once).Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens.Without beam-search, the one-pass propagation much reduces inference time cost of LASO.And because the model is based on the attention based feedforward structure, the computation can be implemented in parallel efficiently.We conduct experiments on publicly available Chinese dataset AISHELL-1.LASO achieves a character error rate of 6.4%, which outperforms the state-of-the-art autoregressive transformer model (6.7%).The average inference latency is 21 ms, which is 1/50 of the autoregressive transformer model.

Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation.Most of the non-autoregressive transformers decode the target sequence from a predefined-length mask sequence.If the predefined length is too long, it will cause a lot of redundant calculations.If the predefined length is shorter than the length of the target sequence, it will hurt the performance of the model.To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.All the experiments are conducted on a public Chinese mandarin dataset AISHELL-1.The results show that the proposed model can accurately predict the length of the target sequence and achieve a competitive performance with the advanced transformers.What's more, the model even achieves a real-time factor of 0.0056, which exceeds all mainstream speech recognition models.

In this article, we propose an end-to-end post-filter method with deep attention fusion features for monaural speaker-independent speech separation. At first, a time-frequency domain speech separation method is applied as the pre-separation stage. The aim of pre-separation stage is to separate the mixture preliminarily. Although this stage can separate the mixture, it still contains the residual interference. In order to enhance the pre-separated speech and improve the separation performance further, the end-to-end post-filter (E2EPF) with deep attention fusion features is proposed. The E2EPF can make full use of the prior knowledge of the pre-separated speech, which contributes to speech separation. It is a fully convolutional speech separation network and uses the waveform as the input features. Firstly, the 1-D convolutional layer is utilized to extract the deep representation features for the mixture and pre-separated signals in the time domain. Secondly, to pay more attention to the outputs of the pre-separation stage, an attention module is applied to acquire deep attention fusion features, which are extracted by computing the similarity between the mixture and the pre-separated speech. These deep attention fusion features are conducive to reduce the interference and enhance the pre-separated speech. Finally, these features are sent to the post-filter to estimate each target signals. Experimental results on the WSJ0-2mix dataset show that the proposed method outperforms the state-of-the-art speech separation method. Compared with the pre-separation method, our proposed method can acquire 64.1%, 60.2%, 25.6% and 7.5% relative improvements in scale-invariant source-to-noise ratio (SI-SNR), the signal-to-distortion ratio (SDR), the perceptual evaluation of speech quality (PESQ) and the short-time objective intelligibility (STOI) measures, respectively.

This paper proposes to use self-attention based model to predict punctuation marks for word sequences. The model is trained using word and speech embedding features which are obtained from the pre-trained Word2Vec and Speech2Vec, respectively. Thus, the model can use any kind of textual data and speech data. Experiments are conducted on English IWSLT2011 datasets. The results show that the self-attention based model trained using word and speech embedding features outperforms the previous state-of-the-art single model by up to 7.8% absolute overall F1-score. The results also show that it obtains performance improvement by up to 4.7% absolute overall F1-score against the previous best ensemble model.

This paper proposes to learn language-invariant bottleneck features from an adversarial end-to-end acoustic model for low resource languages. The multilingual end-to-end model is trained with a connectionist temporal classification loss function. The model has shared and private layers. The shared layers are the hidden layers utilized to learn universal features for all the languages. The private layers are the language-dependent layers used to capture language-specific features. Attention based adversarial end-to-end language identification is used to capture enough language information. Furthermore, orthogonality constraints are used to make private and shared features dissimilar. Experiments are conducted on IARPA Babel datasets. The results show that the target model trained with the proposed language-invariant bottleneck features outperforms the target model trained with the conventional multilingual bottleneck features by up to 9.7% relative word error rate reduction.

Integrating an external language model into a sequence-tosequence speech recognition system is non-trivial.Previous works utilize linear interpolation or a fusion network to integrate external language models.However, these approaches introduce external components, and increase decoding computation.In this paper, we instead propose a knowledge distillation based training approach to integrating external language models into a sequence-to-sequence model.A recurrent neural network language model, which is trained on large scale external text, generates soft labels to guide the sequence-to-sequence model training.Thus, the language model plays the role of the teacher.This approach does not add any external component to the sequence-to-sequence model during testing.And this approach is flexible to be combined with shallow fusion technique together for decoding.The experiments are conducted on public Chinese datasets AISHELL-1 and CLMAD.Our approach achieves a character error rate of 9.3%, which is relatively reduced by 18.42% compared with the vanilla sequenceto-sequence model.

Deep clustering (DC) and utterance-level permutation invariant training (uPIT) have been demonstrated promising for speakerindependent speech separation.DC is usually formulated as two-step processes: embedding learning and embedding clustering, which results in complex separation pipelines and a huge obstacle in directly optimizing the actual separation objectives.As for uPIT, it only minimizes the chosen permutation with the lowest mean square error, doesn't discriminate it with other permutations.In this paper, we propose a discriminative learning method for speaker-independent speech separation using deep embedding features.Firstly, a DC network is trained to extract deep embedding features, which contain each source's information and have an advantage in discriminating each target speakers.Then these features are used as the input for uPIT to directly separate the different sources.Finally, uPIT and DC are jointly trained, which directly optimizes the actual separation objectives.Moreover, in order to maximize the distance of each permutation, the discriminative learning is applied to fine tuning the whole model.Our experiments are conducted on WSJ0-2mix dataset.Experimental results show that the proposed models achieve better performances than DC and uPIT for speaker-independent speech separation.

Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer (SA-T) for speech recognition. RNNs are replaced with self-attention blocks, which are powerful to model long-term dependencies inside sequences and able to be efficiently parallelized. Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance. Additionally, a chunk-flow mechanism is utilized to achieve online decoding. All experiments are conducted on a Mandarin Chinese dataset AISHELL-1. The results demonstrate that our proposed approach achieves a 21.3% relative reduction in character error rate compared with the baseline RNN-T. In addition, the SA-T with chunk-flow mechanism can perform online decoding with only a little degradation of the performance.

The acoustic model trained using the knowledge from the shared hidden layer (SHL) model outperforms the model trained only by using the target language, especially under low resource conditions. However, the shared features may contain some unnecessary language dependent information. It will degrade the performance of the target model. Therefore, this paper proposes language-adversarial transfer learning to alleviate this problem. Adversarial learning is used to ensure that the shared layers of the SHL-model can learn more language invariant features. Experiments are conducted on IARPA Babel datasets. The results show that the target model trained using the knowledge transferred from the adversarial SHL-model achieves up to 10.1% relative word error rate reduction when compared with the target model trained using the knowledge transferred from the SHL-model.

Neural end-to-end TTS such as Tacotron like network can generate very high-quality synthesized speech, and even close to human recording for similar domain text. However, it performs unsatisfactory when scaling it to some challenging test sets. One concern is that the encoder-decoder with attention-based network adopts autoregressive generative sequence model with the limitation of “exposure bias”: errors made early could be quickly amplified, harming subsequent sequence generation. To address this issue, we propose two novel methods, which aim at predicting future by improving the agreement between forward and backward decoding sequence. The first one (denoted as MRBA) is achieved by adding divergence regularization terms to model training objective to maximize the agreement between two directional models, namely L2R (which generates targets from left-to-right) and R2L (which generates targets from right-to-left). While the second one (denoted as BDR) operates on decoder-level and exploits the future information during decoding. By introducing regularization term into the training objective of forward-backward decoders, the forward-decoder's hidden states are forced to be close to the backward-decoder's. Thus, the hidden representations of a unidirectional decoder are encouraged to embed some useful information about the future. Moreover, in order to make forward and backward decoding to improve each other in an interactive process, a joint training method is designed. Experimental results on both English and Mandarin dataset show that our proposed methods especially the second one (BDR), lead to a significantly improvement on both robustness and overall naturalness, as achieving obvious preference advantages in a challenging test, and achieving state-of-the-art performance (outperforming baseline “the revised version of Tacotron2” with a gap of 0.13 and 0.12 for English and Mandarin in MOS, respectively) on a general test.

Conventional continuous emotion recognition consists of feature extraction step followed by regression step. However, the objective of the two steps is not consistent as they are parted. Besides, there is still no consensus about appropriate emotional features. In this study, we propose an end-to-end continuous emotion recognition framework which merges feature extraction and regressor into a unified system. We employ 3D convolutional networks with Long Short-Term Memory Neutral Network (ConvLSTM) to handle spatiotemporal information for continuous emotion recognition. This model is applied on AVEC 2017 database. The experiment results reveal that ConvLSTM model makes a positive effect on the performance improvement, which outperforms the baseline results for arousal of 0.583 vs 0.525 (baseline) and for valence of 0.h54 vs 0.507.

This paper proposes an adversarial multilingual training to train bottleneck (BN) networks for the target language. A parallel shared-exclusive model is also proposed to train the BN network. Adversarial training is used to ensure that the shared layers can learn language-invariant features. Experiments are conducted on IARPA Babel datasets. The results show that the proposed adversarial multilingual BN model outperforms the baseline BN model by up to 8.9% relative word error rate (WER) reduction. The results also show that the proposed parallel shared-exclusive model achieves up to 1.7% relative WER reduction when compared with the stacked share-exclusive model.