This is the summary paper for the AudioMOS Challenge 2025, the very first challenge for automatic subjective quality prediction for synthetic audio. The challenge consists of three tracks. The first track aims to assess text-to-music samples in terms of overall quality and textual alignment. The second track is based on the four evaluation dimensions of Meta Audiobox Aesthetics, and the test set consists of text-to-speech, text-to-audio, and text-to-music samples. The third track focuses on synthetic speech quality assessment in different sampling rates. The challenge attracted 24 unique teams from both academia and industry, and improvements over the baselines were confirmed. The outcome of this challenge is expected to facilitate development and progress in the field of automatic evaluation for audio generation systems.

Quantifying audio aesthetics is challenging due to its subjective nature, influenced by human perception and cultural context. Traditional methods rely on human listeners, leading to inconsistencies and high resource demands. This paper addresses the growing need for automated systems capable of predicting audio aesthetics without human intervention. Such systems are crucial for applications like data filtering, pseudo-labeling, and evaluating generative models.In this paper, we propose new annotation guidelines that break down human listening perspectives into four axes and develop no-reference, peritem prediction models for more nuanced audio quality assessment. Our models are evaluated against human mean opinion scores (MOS) and existing methods, demonstrating comparable or superior performance. This research not only advances the field of audio aesthetics but also provides open-source models and datasets to facilitate future work and benchmarking.

Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48 kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24 kbps bitrate as the baseline AuidoDec and ScoreDec. Objective and subjective evaluations demonstrate the out-of-domain robustness of ComplexDec trained using only the 30-hour VCTK corpus.

We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques. We provide theoretical insights and geometric intuitions for our approach in comparison to ScoreDec as well as another recent work that uses flow matching, and conduct ablation studies on our proposed components. We show that FlowDec is a competitive alternative to the recent GAN-dominated stream of neural codecs, achieving FAD scores better than those of the established GAN-based codec DAC and listening test scores that are on par, and producing qualitatively more natural reconstructions for speech and harmonic structures in music.

Although recent mainstream waveform-domain end-to-end (E2E) neural audio codecs achieve impressive coded audio quality with a very low bitrate, the quality gap between the coded and natural audio is still significant. A generative adversarial network (GAN) training is usually required for these E2E neural codecs because of the difficulty of direct phase modeling. However, such adversarial learning hinders these codecs from preserving the original phase information. To achieve human-level naturalness with a reasonable bitrate, preserve the original phase, and get rid of the tricky and opaque GAN training, we develop a score-based diffusion post-filter (SPF) in the complex spectral domain and combine our previous AudioDec with the SPF to propose ScoreDec, which can be trained using only spectral and score-matching losses. Both the objective and subjective experimental results show that ScoreDec with a 24 kbps bitrate encodes and decodes full-band 48 kHz speech with human-level naturalness and well-preserved phase information.

Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling. The ideal neural audio codec should maintain content, paralinguistics, speaker characteristics, and audio information even at low bitrates. Recently, numerous advanced neural codec models have been proposed. However, codec models are often tested under varying experimental conditions. As a result, we introduce the Codec-SUPERB challenge at SLT 20241, designed to facilitate fair and lightweight comparisons among existing codec models and inspire advancements in the field. This challenge brings together representative speech applications and objective metrics, and carefully selects license-free datasets, sampling them into small sets to reduce evaluation computation costs. This paper presents the challenge’s rules, datasets, participant systems, results, and findings.1https://codecsuperb.github.io/

The trend of scaling up speech generation models poses the threat of biometric information leakage of the identities of the voices in the training data, raising privacy and security concerns. In this letter, we investigate the training of multi-speaker text-to-speech (TTS) models using data that underwent speaker anonymization (SA), a process that tends to hide the speaker identity of the input speech while maintaining other attributes. Two signal processing-based and three deep neural network-based SA methods were used to anonymize VCTK, a multi-speaker TTS dataset, which is further used to train an end-to-end TTS model, VITS, to perform unseen speaker TTS during the testing phase. We conducted extensive objective and subjective experiments to evaluate the anonymized training data, as well as the performance of the downstream TTS model trained using those data. Importantly, we found that UTMOS, a data-driven subjective rating predictor model, and GVD, a metric that measures the gain of voice distinctiveness, are good indicators of the downstream TTS performance. We summarize insights in the hope of helping future researchers determine the usefulness of the SA system for multi-speaker TTS training.

Remote photoplethysmography (rPPG) has been used to measure vital signs such as heart rate, heart rate variability, blood pressure (BP), and blood oxygen. Recent studies adopt features developed with photoplethysmography (PPG) to achieve contactless BP measurement via rPPG. These features can be classified into two groups: time or phase differences from multiple signals, or waveform feature analysis from a single signal. Here we devise a solution to extract the time difference information from the rPPG signal captured at 30 FPS. We also propose a deep learning model architecture to estimate BP from the extracted features. To prevent overfitting and compensate for the lack of data, we leverage a multi-model design and generate synthetic data. We also use subject information related to BP to assist in model learning. For real-world usage, the subject information is replaced with values estimated from face images, with performance that is still better than the state-of-the-art. To our best knowledge, the improvements can be achieved because of: 1) the model selection with estimated subject information, 2) replacing the estimated subject information with the real one, 3) the InfoGAN assistance training (synthetic data generation), and 4) the time difference features as model input. To evaluate the performance of the proposed method, we conduct a series of experiments, including dynamic BP measurement for many single subjects and nighttime BP measurement with infrared lighting. Our approach reduces the MAE from 15.49 to 8.78 mmHg for systolic blood pressure (SBP) and 10.56 to 6.16 mmHg for diastolic blood pressure(DBP) on a self-constructed rPPG dataset. On the Taipei Veterans General Hospital(TVGH) dataset for nighttime applications, the MAE is reduced from 21.58 to 11.12 mmHg for SBP and 9.74 to 7.59 mmHg for DBP, with improvement ratios of 48.47% and 22.07% respectively.

Atrial Fibrillation (AF) screening from face videos has become popular with the trend of telemedicine and telehealth in recent years. In this study, the largest facial image database for camera-based AF detection is proposed. There are 657 participants from two clinical sites and each of them is recorded for about 10 minutes of video data, which can be further processed as over 10 000 segments around 30 seconds, where the duration setting is referred to the guideline of AF diagnosis. It is also worth noting that, 2 979 segments are segment-wise labeled, that is, every rhythm is independently labeled with AF or not. Besides, all labels are confirmed by the cardiologist manually. Various environments, talking, facial expressions, and head movements are involved in data collection, which meets the situations in practical usage. Specific to camera-based AF screening, a novel CNN-based architecture equipped with an attention mechanism is proposed. It is capable of fusing heartbeat consistency, heart rate variability derived from remote photoplethysmography, and motion features simultaneously to reliable outputs. With the proposed model, the performance of intra-database evaluation comes up to 96.62% of sensitivity, 90.61% of specificity, and 0.96 of AUC. Furthermore, to check the capability of adaptation of the proposed method thoroughly, the cross-database evaluation is also conducted, and the performance also reaches about 90% on average with the AUCs being over 0.94 in both clinical sites.

A good audio codec for live applications such as telecommunication is characterized by three key properties: (1) compression, i.e. the bitrate that is required to transmit the signal should be as low as possible; (2) latency, i.e. encoding and decoding the signal needs to be fast enough to enable communication without or with only minimal noticeable delay; and (3) reconstruction quality of the signal. In this work, we propose an open-source, streamable, and real-time neural audio codec that achieves strong performance along all three axes: it can reconstruct highly natural sounding 48 kHz speech signals while operating at only 12 kbps and running with less than 6 ms (GPU)/10 ms (CPU) latency. An efficient training paradigm is also demonstrated for developing such neural audio codecs for real-world scenarios. Both objective and subjective evaluations using the VCTK corpus are provided. To sum up, AudioDec is a well-developed plug-and-play benchmark for audio codec applications.

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source- filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch controllability. However, the high temporal resolution inputs result in high computation costs. Although the HiFi-GAN vocoder achieves fast high-fidelity voice generation thanks to the efficient upsampling-based generator architecture, the pitch controllability is severely limited. To realize a fast and pitch- controllable high-fidelity neural vocoder, we introduce the source-filter theory into HiFi-GAN by hierarchically conditioning the resonance filtering network on a well-estimated source excitation information. According to the experimental results, our proposed method outperforms HiFi-GAN and uSF- GAN on a singing voice generation in voice quality and synthesis speed on a single CPU. Furthermore, unlike the uSFGAN vocoder, the proposed method can be easily adopted/integrated in real-time applications and end-to-end systems.

Complex emotion is an aggregate of two or more others which has highly variable appearances, inter-dependence, and affective dynamics.These properties make the recognition hard to handle via existing recognition techniques like action units or valence-arousal detection. In this study, we propose a bionic two-system structure for complex emotion recognition. The structure mimics the working theory of the human brain responding to problems decision-making. System I is a fast compound sensing module. System II is a slower cognitive decision module that processes data more integratively. System I contains one branch for facial expression feature representation including basic emotion, action units, and valence arousal detection and one for physiological measurement which is an image-only implementation for practicality. In System II, a decision module with segmentation is employed to ensure the chosen period including the emotion occurrence and iteratively optimize the emotion information in a given segment via reinforcement learning. The proposed method outperforms state-of-the-art on emotion recognition tasks with an accuracy of 94.15% in basic emotion recognition on the BP4D and an accuracy of 68.75% for binary valence arousal classification on the DEAP. For a subset of complex emotions, the recognition accuracy exceeds 70% on both databases, that is a significant improvement.

We introduce unified source-filter generative adversarial networks (uSFGAN), a waveform generative model conditioned on acoustic features, which represents the source-filter architecture in a generator network. Unlike the previous neural-based source-filter models in which parametric signal process modules are combined with neural networks, our approach enables unified optimization of both the source excitation generation and resonance filtering parts to achieve higher sound quality. In the uSFGAN framework, several specific regularization losses are proposed to enable the source excitation generation part to output reasonable source excitation signals. Both objective and subjective experiments are conducted, and the results demonstrate that the proposed uSFGAN achieves comparable sound quality to HiFi-GAN in the speech reconstruction task and outperforms WORLD in the$\text{F}_{0}$transformation task. Moreover, we argue that the$\text{F}_{0}$-driven mechanism and the inductive bias obtained by source-filter modeling improve the robustness against unseen$\text{F}_{0}$in training as shown by the results of experimental evaluations. Audio samples are available at our demo site athttps://chomeyama.github.io/PitchControllableNeuralVocoder-Demo/.

Beyond the conventional voice conversion (VC) where the speaker information is converted without altering the linguistic content, the background sounds are informative and need to be retained in some real-world scenarios, such as VC in movie/video and VC in music where the voice is entangled with background sounds. As a new VC framework, we have developed a noisy-to-noisy (N2N) VC framework to convert the speaker’s identity while preserving the background sounds. Although our framework consisting of a denoising module and a VC module well handles the background sounds, the VC module is sensitive to the distortion caused by the denoising module. To address this distortion issue, in this paper we propose the improved VC module to directly model the noisy speech waveform while controlling the background sounds. The experimental results have demonstrated that our improved framework significantly outperforms the previous one and achieves an acceptable score in terms of naturalness, while reaching comparable similarity performance to the upper bound of our framework.

This paper introduces a unified source-filter network with a harmonic-plus-noise source excitation generation mechanism. In our previous work, we proposed unified Source-Filter GAN (uSFGAN) for developing a high-fidelity neural vocoder with flexible voice controllability using a unified source-filter neural network architecture. However, the capability of uSFGAN to model the aperiodic source excitation signal is insufficient, and there is still a gap in sound quality between the natural and generated speech. To improve the source excitation modeling and generated sound quality, a new source excitation generation network separately generating periodic and aperiodic components is proposed. The advanced adversarial training procedure of HiFiGAN is also adopted to replace that of Parallel WaveGAN used in the original uSFGAN. Both objective and subjective evaluation results show that the modified uSFGAN significantly improves the sound quality of the basic uSFGAN while maintaining the voice controllability.

Without the need of a clean reference, non-intrusive speech assessment methods have caught great attention for objective evaluations. Recently, deep neural network (DNN) models have been applied to build non-intrusive speech assessment approaches and confirmed to provide promising performance. However, most DNN-based approaches are designed for normal-hearing listeners without considering hearing-loss factors. In this study, we propose a DNN-based hearing aid speech assessment network (HASA-Net), formed by a bidirectional long short-term memory (BLSTM) model, to predict speech quality and intelligibility scores simultaneously according to input speech signals and specified hearing-loss patterns. To the best of our knowledge, HASA-Net is the first work to incorporate quality and intelligibility assessments utilizing a unified DNN-based non-intrusive model for hearing aids. Experimental results show that the predicted speech quality and intelligibility scores of HASA-Net are highly correlated to two well-known intrusive hearing-aid evaluation metrics, hearing aid speech quality index (HASQI) and hearing aid speech perception index (HASPI), respectively.

We present a novel approach to any-to-one (A2O) voice conversion (VC) in a sequence-to-sequence (seq2seq) framework. A2O VC aims to convert any speaker, including those unseen during training, to a fixed target speaker. We utilize vq-wav2vec (VQW2V), a discretized self-supervised speech representation that was learned from massive unlabeled data, which is assumed to be speaker-independent and well corresponds to underlying linguistic contents. Given a training dataset of the target speaker, we extract VQW2V and acoustic features to estimate a seq2seq mapping function from the former to the latter. With the help of a pretraining method and a newly designed postprocessing technique, our model can be generalized to only 5 min of data, even outperforming the same model trained with parallel data.

In this paper, we present an open-source software for developing a nonparallel voice conversion (VC) system named crank. Although we have released an open-source VC software based on the Gaussian mixture model named sprocket in the last VC Challenge, it is not straightforward to apply any speech corpus because it is necessary to prepare parallel utterances of source and target speakers to model a statistical conversion function. To address this issue, in this study, we developed a new open-source VC software that enables users to model the conversion function by using only a nonparallel speech corpus. For implementing the VC software, we used a vector-quantized variational autoencoder (VQVAE). To rapidly examine the effectiveness of recent technologies developed in this research field, crank also supports several representative works for autoencoder-based VC methods such as the use of hierarchical architectures, cyclic architectures, generative adversarial networks, speaker adversarial training, and neural vocoders. Moreover, it is possible to automatically estimate objective measures such as mel-cepstrum distortion and pseudo mean opinion score based on MOSNet. In this paper, we describe representative functions developed in crank and make brief comparisons by objective evaluations.

Nowadays, neural vocoders can generate very high-fidelity speech when a bunch of training data is available.Although a speaker-dependent (SD) vocoder usually outperforms a speaker-independent (SI) vocoder, it is impractical to collect a large amount of data of a specific target speaker for most realworld applications.To tackle the problem of limited target data, a data augmentation method based on speaker representation and similarity measurement of speaker verification is proposed in this paper.The proposed method selects utterances that have similar speaker identity to the target speaker from an external corpus, and then combines the selected utterances with the limited target data for SD vocoder adaptation.The evaluation results show that, compared with the vocoder adapted using only limited target data, the vocoder adapted using augmented data improves both the quality and similarity of synthesized speech.

We propose a unified approach to data-driven source-filter modeling using a single neural network for developing a neural vocoder capable of generating high-quality synthetic speech waveforms while retaining flexibility of the source-filter model to control their voice characteristics. Our proposed network called unified source-filter generative adversarial networks (uSFGAN) is developed by factorizing quasi-periodic parallel WaveGAN (QPPWG), one of the neural vocoders based on a single neural network, into a source excitation generation network and a vocal tract resonance filtering network by additionally implementing a regularization loss. Moreover, inspired by neural source filter (NSF), only a sinusoidal waveform is additionally used as the simplest clue to generate a periodic source excitation waveform while minimizing the effect of approximations in the source filter model. The experimental results demonstrate that uSFGAN outperforms conventional neural vocoders, such as QPPWG and NSF in both speech quality and pitch controllability.

Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. Nonetheless, without sufficient data, seq2seq VC models can suffer from unstable training and mispronunciation problems in the converted speech, thus far from practical. To tackle these shortcomings, we propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR). We argue that VC models initialized with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech. In this work, we examine our proposed method in a parallel, one-to-one setting. We employed recurrent neural network (RNN)-based and Transformer based models, and through systematical experiments, we demonstrate the effectiveness of the pretraining scheme and the superiority of Transformer based models over RNN-based models in terms of intelligibility, naturalness, and similarity.

In this paper, we propose a quasi-periodic parallel WaveGAN (QPPWG) waveform generative model, which applies a quasi-periodic (QP) structure to a parallel WaveGAN (PWG) model using pitch-dependent dilated convolution networks (PDCNNs). PWG is a small-footprint GAN-based raw waveform generative model, whose generation time is much faster than real time because of its compact model and non-autoregressive (non-AR) and non-causal mechanisms. Although PWG achieves high-fidelity speech generation, the generic and simple network architecture lacks pitch controllability for an unseen auxiliary fundamental frequency (F0) feature such as a scaled F0. To improve the pitch controllability and speech modeling capability, we apply a QP structure with PDCNNs to PWG, which introduces pitch information to the network by dynamically changing the network architecture corresponding to the auxiliary F0feature. Both objective and subjective experimental results show that QPPWG outperforms PWG when the auxiliary F0feature is scaled. Moreover, analyses of the intermediate outputs of QPPWG also show better tractability and interpretability of QPPWG, which respectively models spectral and excitation-like signals using the cascaded fixed and adaptive blocks of the QP structure.

In this paper, a pitch-adaptive waveform generative model named Quasi-Periodic WaveNet (QPNet) is proposed to improve the limited pitch controllability of vanilla WaveNet (WN) using pitch-dependent dilated convolution neural networks (PDCNNs). Specifically, as a probabilistic autoregressive generation model with stacked dilated convolution layers, WN achieves high-fidelity audio waveform generation. However, the pure-data-driven nature and the lack of prior knowledge of audio signals degrade the pitch controllability of WN. For instance, it is difficult for WN to precisely generate the periodic components of audio signals when the given auxiliary fundamental frequency (F0) features are outside the F0range observed in the training data. To address this problem, QPNet with two novel designs is proposed. First, the PDCNN component is applied to dynamically change the network architecture of WN according to the given auxiliary F0features. Second, a cascaded network structure is utilized to simultaneously model the long- and short-term dependencies of quasi-periodic signals such as speech. The performances of single-tone sinusoid and speech generations are evaluated. The experimental results show the effectiveness of the PDCNNs for unseen auxiliary F0features and the effectiveness of the cascaded structure for speech generation.

This paper presents a novel way for an efficient implementation scheme of shallow WaveNet vocoder with multiple samples (segment) output based on the use of Laplacian distribution and linear prediction. In our previous work, we have proposed a shallow architecture for WaveNet vocoder that utilizes only 9 dilated convolutional layers while capable of generating high-quality speech with the use of Laplacian distribution in speech samples modeling. However, there is still a lot of room for improvements to increase the computation efficiency, such as by the inference of segment output and the use of a more compact structure. In this work, we tackle this issue by proposing a simple implementation scheme of segment output modeling, that can be easily extended into other neural vocoders, where the Laplacian distribution parameters of multiple samples are estimated simultaneously. Further, to preserve the dependencies of the samples within the segment, we also propose utilizing linear prediction (LP) to compute the distribution parameters, where data- driven LP-coefficients are estimated by the WaveNet vocoder along with locations and scales. Finally, a shallower WaveNet vocoder with 6 layers is deployed. The experimental results demonstrate that the proposed LP-based Laplacian distribution can alleviate the quality degradation caused by segment generation.

We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining.Seq2seq VC models are attractive owing to their ability to convert prosody.While seq2seq models based on recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been successfully applied to VC, the use of the Transformer network, which has shown promising results in various speech processing tasks, has not yet been investigated.Nonetheless, their data-hungry property and the mispronunciation of converted speech make seq2seq models far from practical.To this end, we propose a simple yet effective pretraining technique to transfer knowledge from learned TTS models, which benefit from large-scale, easily accessible TTS corpora.VC models initialized with such pretrained model parameters are able to generate effective hidden representations for high-fidelity, highly intelligible converted speech.Experimental results show that such a pretraining scheme can facilitate data-efficient training and outperform an RNN-based seq2seq VC model in terms of intelligibility, naturalness, and similarity.

We present a novel approach of cyclic spectral modeling for unsupervised discovery of speech units into voice conversion with excitation network and waveform modeling.Specifically, we propose two spectral modeling techniques: 1) cyclic vectorquantized autoencoder (CycleVQVAE), and 2) cyclic variational autoencoder (CycleVAE).In CycleVQVAE, a discrete latent space is used for the speech units, whereas, in Cycle-VAE, a continuous latent space is used.The cyclic structure is developed using the reconstruction flow and the cyclic reconstruction flow of spectral features, where the latter is obtained by recycling the converted spectral features.This method is used to obtain a possible speaker-independent latent space because of marginalization on all possible speaker conversion pairs during training.On the other hand, speaker-dependent space is conditioned with a one-hot speaker-code.Excitation modeling is developed in a separate manner for CycleVQVAE, while it is in a joint manner for CycleVAE.To generate speech waveform, WaveNet-based waveform modeling is used.The proposed framework is entried for the ZeroSpeech Challenge 2020, and is capable of reaching a character error rate of 0.21, a speaker similarity score of 3.91, a mean opinion score of 3.84 for the naturalness of the converted speech in the 2019 voice conversion task.

In this paper, we propose a parallel WaveGAN (PWG)-like neural vocoder with a quasi-periodic (QP) architecture to improve the pitch controllability of PWG. PWG is a compact non-autoregressive (non-AR) speech generation model, whose generative speed is much faster than real time. While utilizing PWG as a vocoder to generate speech on the basis of acoustic features such as spectral and prosodic features, PWG generates high-fidelity speech. However, when the input acoustic features include unseen pitches, the pitch accuracy of PWG-generated speech degrades because of the fixed and generic network of PWG without prior knowledge of speech periodicity. The proposed QPPWG adopts a pitch-dependent dilated convolution network (PDCNN) module, which introduces the pitch information into PWG via the dynamically changed network architecture, to improve the pitch controllability and speech modeling capability of vanilla PWG. Both objective and subjective evaluation results show the higher pitch accuracy and comparable speech quality of QPPWG-generated speech when the QPPWG model size is only 70 % of that of vanilla PWG.

Recently, the effectiveness of text-to-speech (TTS) systems combined with neural vocoders to generate high-fidelity speech has been shown.However, collecting the required training data and building these advanced systems from scratch are time and resource consuming.An economical approach is to develop a neural vocoder to enhance the speech generated by existing or low-cost TTS systems.Nonetheless, this approach usually suffers from two issues: 1) temporal mismatches between TTS and natural waveforms and 2) acoustic mismatches between training and testing data.To address these issues, we adopt a cyclic voice conversion (VC) model to generate temporally matched pseudo-VC data for training and acoustically matched enhanced data for testing the neural vocoders.Because of the generality, this framework can be applied to arbitrary TTS systems and neural vocoders.In this paper, we apply the proposed method with a state-of-the-art WaveNet vocoder for two different basic TTS systems, and both objective and subjective experimental results confirm the effectiveness of the proposed framework.

This paper presents an effective way to extract low-level features based on sparse coding for facial occlusion detection. Masked Neural Sparse Encoder (MNSE) is proposed to be a sparse coding solver that brings out better feature bases for data representation and improvement in the anomaly detection task. To guarantee the representational capability of features, a set of masks is applied to force each feature basis is heeded on learning a specific stroke within a certain area. The mask set is constructed by clustering primary strokes from training samples, and represents them with corresponding centers of clusters. Hence, these masks stand for main strokes in concerned areas with higher probabilities. Experiments show MNSE contains better representational capability in data from different domains. Compared with the standard sparse coding and the auto-encoder based approaches, MNSE lifts the accuracy up around 20%.

This paper presents a novel framework for providing high-quality parallel voice conversion (VC) using a cyclic recurrent neural network (RNN) and a finely tuned WaveNet vocoder. Using the proposed system, we are tackling the quality degradation issue faced by WaveNet when it is fed with estimated (oversmoothed) speech features, such as mel-cepstrum parameters predicted from a statistical model. In VC, providing predicted features to fine-tune a pretrained WaveNet model is not straightforward owing to the difference in time-sequence alignment. To overcome this problem, we propose the use of a cyclic spectral conversion network that is capable of performing a conversion flow, i.e., source-to-target, and a cyclic flow, i.e., generate self-predicted target speaker features, and is trained by using both the conversion and cyclic losses. The experimental results demonstrate that, overall, the proposed system significantly improves the converted speech, resulting in a mean opinion score of 3.79 and a speaker similarity score of 73.86%.

In this work, we investigate the effectiveness of two techniques for improving variational autoencoder (VAE) based voice conversion (VC). First, we reconsider the relationship between vocoder features extracted using the high quality vocoders adopted in conventional VC systems, and hypothesize that the spectral features are in fact F0 dependent. Such hypothesis implies that during the conversion phase, the latent codes and the converted features in VAE based VC are in fact source F0 dependent. To this end, we propose to utilize the F0 as an additional input of the decoder. The model can learn to disentangle the latent code from the F0 and thus generates converted F0 dependent converted features. Second, to better capture temporal dependencies of the spectral features and the F0 pattern, we replace the frame wise conversion structure in the original VAE based VC framework with a fully convolutional network structure. Our experiments demonstrate that the degree of disentanglement as well as the naturalness of the converted speech are indeed improved.

In this paper, we present a novel technique for a non-parallel voice conversion (VC) with the use of cyclic variational autoencoder (CycleVAE)-based spectral modeling.In a variational autoencoder (VAE) framework, a latent space, usually with a Gaussian prior, is used to encode a set of input features.In a VAE-based VC, the encoded latent features are fed into a decoder, along with speaker-coding features, to generate estimated spectra with either the original speaker identity (reconstructed) or another speaker identity (converted).Due to the non-parallel modeling condition, the converted spectra can not be directly optimized, which heavily degrades the performance of a VAEbased VC.In this work, to overcome this problem, we propose to use CycleVAE-based spectral model that indirectly optimizes the conversion flow by recycling the converted features back into the system to obtain corresponding cyclic reconstructed spectra that can be directly optimized.The cyclic flow can be continued by using the cyclic reconstructed features as input for the next cycle.The experimental results demonstrate the effectiveness of the proposed CycleVAE-based VC, which yields higher accuracy of converted spectra, generates latent features with higher correlation degree, and significantly improves the quality and conversion accuracy of the converted speech.

In this paper, we propose a quasi-periodic neural network (QPNet) vocoder with a novel network architecture named pitch-dependent dilated convolution (PDCNN) to improve the pitch controllability of WaveNet (WN) vocoder. The effectiveness of the WN vocoder to generate high-fidelity speech samples from given acoustic features has been proved recently. However, because of the fixed dilated convolution and generic network architecture, the WN vocoder hardly generates speech with given F0 values which are outside the range observed in training data. Consequently, the WN vocoder lacks the pitch controllability which is one of the essential capabilities of conventional vocoders. To address this limitation, we propose the PDCNN component which has the time-variant adaptive dilation size related to the given F0 values and a cascade network structure of the QPNet vocoder to generate quasi-periodic signals such as speech. Both objective and subjective tests are conducted, and the experimental results demonstrate the better pitch controllability of the QPNet vocoder compared to the same and double sized WN vocoders while attaining comparable speech qualities. Index Terms: WaveNet, vocoder, quasi-periodic signal, pitch-dependent dilated convolution, pitch controllability

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder.The effectiveness of the WaveNet vocoder for generating natural speech from acoustic features has been proved in recent works.However, it sometimes generates very noisy speech with collapsed speech segments when only a limited amount of training data is available or significant acoustic mismatches exist between the training and testing data.Such a limitation on the corpus and limited ability of the model can easily occur in some speech generation applications, such as voice conversion and speech enhancement.To address this problem, we propose a technique to automatically detect collapsed speech segments.Moreover, to refine the detected segments, we also propose a waveform generation technique for WaveNet using a linear predictive coding constraint.Verification and subjective tests are conducted to investigate the effectiveness of the proposed techniques.The verification results indicate that the detection technique can detect most collapsed segments.The subjective evaluations of voice conversion demonstrate that the generation technique significantly improves the speech quality while maintaining the same speaker similarity.

This paper presents an evaluation of deep spectral mapping and WaveNet vocoder in voice conversion (VC). In our VC framework, spectral features of an input speaker are converted into those of a target speaker using the deep spectral mapping, and then together with the excitation features, the converted waveform is generated using WaveNet vocoder. In this work, we compare three different deep spectral mapping networks, i.e., a deep single density network (DSDN), a deep mixture density network (DMDN), and a long short-term memory recurrent neural network with an autoregressive output layer (LSTM-AR). Moreover, we also investigate several methods for reducing mismatches of spectral features used in WaveNet vocoder between training and conversion processes, such as some methods to alleviate oversmoothing effects of the converted spectral features, and another method to refine WaveNet using the converted spectral features. The experimental results demonstrate that the LSTM-AR yields nearly better spectral mapping accuracy than the others, and the proposed WaveNet refinement method significantly improves the naturalness of the converted waveform.

This paper presents a novel postfiltering approach based on the locally linear embedding (LLE) algorithm for speech enchantment (SE). The aim of the proposed LLE-based postfiltering approach is to further remove the residual noise components from the SE-processed speech signals through a spectral conversion process, thereby increasing the signal-to-noise ratio (SNR) and speech quality. The proposed postfiltering approach consists of two phases. In the offline phase, paired SE-processed and clean speech exemplars are prepared for dictionary construction. In the online phase, the LLE algorithm is adopted to convert the SE-processed speech signals to the clean ones. The present study integrates the LLE-based postfiltering approach with a deep denoising autoencoder (DDAE) SE method, which has been confirmed to provide outstanding capability for noise reduction. Experimental results show that the proposed postfiltering approach can notably enhance the DDAE-based SE processed speech signals in different noise types and SNR levels.

Building a voice conversion (VC) system from non-parallel speech corpora is challenging but highly valuable in real application scenarios.In most situations, the source and the target speakers do not repeat the same texts or they may even speak different languages.In this case, one possible, although indirect, solution is to build a generative model for speech.Generative models focus on explaining the observations with latent variables instead of learning a pairwise transformation function, thereby bypassing the requirement of speech frame alignment.In this paper, we propose a non-parallel VC framework with a variational autoencoding Wasserstein generative adversarial network (VAW-GAN) that explicitly considers a VC objective when building the speech model.Experimental results corroborate the capability of our framework for building a VC system from unaligned data, and demonstrate improved conversion quality.