Although current large audio language models (LALMs) extend text large language models (LLMs) with generic acoustic understanding abilities, they usually suffer from prompt sensitivity, where different instructions of the same intention can yield drastically different outcomes. In this work, we propose AHAMask, where we simply mask some of the attention heads in the decoder-only LLM backbone of LALMs, to trigger specific acoustic task functionalities without instructions. These masks are efficiently obtained by training on an LALM, with the number of trainable parameters equal to the attention head count in its LLM backbone. We show by experiments that applying such selective attention head masks achieves comparable or even better performance than using instructions, either on single or composite tasks. Besides achieving reliable acoustic task specification for LALMs, this also reveals that LALMs exhibit certain ``functional pathways'' in their attention heads.

Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining the unknown number of sound sources, TSE approaches require precisely specified clues to achieve optimal performance. This paper proposes a unified framework that synergistically combines SS and TSE to overcome their individual limitations. Our architecture employs two complementary components: 1) An Encoder-Decoder Attractor (EDA) network that automatically infers both the source count and corresponding acoustic clues for SS, and 2) A multi-modal fusion network that precisely interprets diverse user-provided clues (acoustic, semantic, or visual) for TSE. Through joint training with cross-task consistency constraints, we establish a unified latent space that bridges both paradigms. During inference, the system adaptively operates in either fully autonomous SS mode or clue-driven TSE mode. Experiments demonstrate remarkable performance in both tasks, with notable improvements of 1.4 dB SDR improvement in SS compared to baseline and 86% TSE accuracy.

In complex multi-speaker scenarios with significant speaker overlap and background noise, extracting the target speaker's speech remains a major challenge. This capability is crucial for dialogue-based applications such as AI speech assistants, where downstream tasks such as speech recognition depend on clean speech. A potential solution to address these challenges is Target Speaker Extraction (TSE), which leverages auxiliary information to extract target speech from mixed and noisy speech, thus overcoming the limitations of Speech Separation (SS) and Speech Enhancement (SE). In particular, we propose a multi-modal TSE network, namely Text Prompt Extractor with echo cue block (TPEech), which uses historical dialogue text as cues for extraction and incorporates the echo cue block (ECB) to further exploit this cue and enhance TSE performance. The experiments show the excellent extraction and denoising capabilities of our proposed network. TPEech achieves an SI-SDRi of 9.632 dB, an SDR of 13.045 dB, a PESQ of 2.814, and a STOI of 0.885, outperforming competitive baselines. Additionally, we experimentally verify that TPEech is robust against semantically incomplete textual prompts. Dataset and source code will be publicly available.

Rap, a prominent genre of vocal performance, remains underexplored in vocal generation. General vocal synthesis depends on precise note and duration inputs, requiring users to have related musical knowledge, which limits flexibility. In contrast, rap typically features simpler melodies, with a core focus on a strong rhythmic sense that harmonizes with accompanying beats. In this paper, we propose Freestyler, the first system that generates rapping vocals directly from lyrics and accompaniment inputs. Freestyler utilizes language model-based token generation, followed by a conditional flow matching model to produce spectrograms and a neural vocoder to restore audio. It allows a 3-second prompt to enable zero-shot timbre control. Due to the scarcity of publicly available rap datasets, we also present RapBank, a rap song dataset collected from the internet, alongside a meticulously designed processing pipeline. Experimental results show that Freestyler produces high-quality rapping voice generation with enhanced naturalness and strong alignment with accompanying beats, both stylistically and rhythmically.

The emergence of novel generative modeling paradigms, particularly audio language models, has significantly advanced the field of song generation. Although state-of-the-art models are capable of synthesizing both vocals and accompaniment tracks up to several minutes long concurrently, research about partial adjustments or editing of existing songs is still underexplored, which allows for more flexible and effective production. In this paper, we present SongEditor, the first song editing paradigm that introduces the editing capabilities into language-modeling song generation approaches, facilitating both segment-wise and track-wise modifications. SongEditor offers the flexibility to adjust lyrics, vocals, and accompaniments, as well as synthesizing songs from scratch. The core components of SongEditor include a music tokenizer, an autoregressive language model, and a diffusion generator, enabling generating an entire section, masked lyrics, or even separated vocals and background music. Extensive experiments demonstrate that the proposed SongEditor achieves exceptional performance in end-to-end song editing, as evidenced by both objective and subjective metrics.

Songs, as a central form of musical art, exemplify the richness of human intelligence and creativity. While recent advances in generative modeling have enabled notable progress in long-form song generation, current systems for fulllength song synthesis still face major challenges, including data imbalance, insufficient controllability, and inconsistent musical quality. DiffRhythm, a pioneering diffusion-based model, advanced the field by generating full-length songs with expressive vocals and accompaniment. However, its performance was constrained by an unbalanced model training dataset and limited controllability over musical style, resulting in noticeable quality disparities and restricted creative flexibility. To address these limitations, we propose DiffRhythm+, an enhanced diffusionbased framework for controllable and flexible full-length song generation. DiffRhythm+ leverages a substantially expanded and balanced training dataset to mitigate issues such as repetition and omission of lyrics, while also fostering the emergence of richer musical skills and expressiveness. The framework introduces a multi-modal style conditioning strategy, enabling users to precisely specify musical styles through both descriptive text and reference audio, thereby significantly enhancing creative control and diversity. We further introduce direct performance optimization aligned with user preferences, guiding the model toward consistently preferred outputs across evaluation metrics. Extensive experiments demonstrate that DiffRhythm+ achieves significant improvements in naturalness, arrangement complexity, and listener satisfaction over previous systems. Audio samples are available at https://longwaytog0.github.io/DiffRhythmPlus/.

In real-world voice conversion applications, environmental noise in source speech and user demands for expressive output pose critical challenges. Traditional ASR-based methods ensure noise robustness but suppress prosody richness, while SSL-based models improve expressiveness but suffer from timbre leakage and noise sensitivity. This paper proposes REF-VC, a noise-robust expressive voice conversion system. Key innovations include: (1) A random erasing strategy to mitigate the information redundancy inherent in SSL features, enhancing noise robustness and expressiveness; (2) Implicit alignment inspired by E2TTS to suppress non-essential feature reconstruction; (3) Integration of Shortcut Models to accelerate flow matching inference, significantly reducing to 4 steps. Experimental results demonstrate that REF-VC outperforms baselines such as Seed-VC in zero-shot scenarios on the noisy set, while also performing comparably to Seed-VC on the clean set. In addition, REF-VC can be compatible with singing voice conversion within one model. The samples can be found at: https://rxyj.github.io/asru2025/

Speaker diarization is typically considered as a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore for the first time the use of neural network-based generative methods for speaker diarization. We implement a Flow-Matching (FM) based generative algorithm within the sequenceto-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm, and our proposed Flow-TSVAD method can significantly outperform the traditional Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, only requiring two inference steps to achieve promising results. Moreover, as a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times, so the ensemble system combining the results from various sampling instances can further boost the diarization performance.

Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hallucination issues such as mispronunciation, word skipping and repeating. To address this limitation, we propose VALL-T, a generative Transducer model that introduces shifting relative position embeddings for input phoneme sequence, explicitly indicating the monotonic generation process while maintaining the architecture of decoder-only Transformer. Consequently, VALL-T retains the capability of prompt-based zero-shot adaptation and demonstrates better robustness against hallucinations with a relative reduction of 28.3% in the word error rate. The audio samples are available at https://cpdu.github.io/vallt.

In accented voice conversion or accent conversion, we seek to convert the accent in speech from one another while preserving speaker identity and semantic content. In this study, we formulate a novel method for creating multi-accented speech samples, thus pairs of accented speech samples by the same speaker, through text transliteration for training accent conversion systems. We begin by generating transliterated text with Large Language Models (LLMs), which is then fed into multilingual TTS models to synthesize accented English speech. As a reference system, we built a sequence-to-sequence model on the synthetic parallel corpus for accent conversion. We validated the proposed method for both native and non-native English speakers. Subjective and objective evaluations further validate our dataset’s effectiveness in accent conversion studies.

This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation. The training of E1 TTS is straightforward; it does not require explicit monotonic alignment between the text and audio pairs. The inference of E1 TTS is efficient, requiring only one neural network evaluation for each utterance. Despite its sampling efficiency, E1 TTS achieves naturalness and speaker similarity comparable to various strong baseline models. Audio samples are available at e1tts.github.io.

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model’s generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline.

Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world scenarios, visual cues are not always available due to various impairments, which undermines the stability of AV-TSE. Despite this challenge, humans can maintain attentional momentum over time, even when the target speaker is not visible. In this paper, we introduce the Momentum Multi-modal target Speaker Extraction (MoMuSE), which retains a speaker identity momentum in memory, enabling the model to continuously track the target speaker. Designed for real-time inference, MoMuSE extracts the current speech window with guidance from both visual cues and dynamically updated speaker momentum. Experimental results demonstrate that MoMuSE exhibits significant improvement, particularly in scenarios with severe impairment of visual cues.

Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of songs and the scarcity of high-quality data, leading to limitations in audio quality, musicality, instruction following, and vocal-instrument harmony. To address these challenges, we introduce LeVo, a language model based framework consisting of LeLM and Music Codec. LeLM is capable of parallel modeling of two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve better vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. It employs two decoder-only transformers and a modular extension training strategy to prevent interference between different token types. To further enhance musicality and instruction following ability, we introduce a multi-preference alignment method based on Direct Preference Optimization (DPO). This method handles diverse human preferences through a semi-automatic data construction process and post-training. Experimental results demonstrate that LeVo significantly outperforms existing open-source methods in both objective and subjective metrics, while performing competitively with industry systems. Ablation studies further justify the effectiveness of our designs. Audio examples and source code are available at https://levo-demo.github.io and https://github.com/tencent-ailab/songgeneration.

Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with local fidelity, resulting in outputs that lack musicality or suffer from incoherent progression and mismatched lyrics. This paper introduces SongBloom, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms. Audio samples are available on our demo page: https://cypress-yang.github.io/SongBloom_demo.

In speaker verification, we use computational method to verify if an utterance matches the identity of an enrolled speaker. This task is similar to the manual task of forensic voice comparison, where linguistic analysis is combined with auditory measurements to compare and evaluate voice samples. Despite much success, we have yet to develop a speaker verification system that offers explainable results comparable to those from manual forensic voice comparison. A novel approach, Explainable Phonetic Trait-Oriented (ExPO) network, is proposed in this letter to introduce the speaker'sphonetic traitwhich describes the speaker's characteristics at the phonetic level, resembling what forensic comparison does. ExPO not only generates utterance-level speaker embeddings but also allows for fine-grained analysis and visualization of phonetic traits, offering an explainable speaker verification process. Furthermore, we investigate phonetic traits from within-speaker and between-speaker variation perspectives to determine which trait is most effective for speaker verification, marking an important step towards explainable speaker verification.

Emotional text-to-speech synthesis (TTS) aims to generate realistic emotional speech from input text. However, quantitatively controlling multi-level emotion rendering remains challenging. In this paper, we propose a flow-matching based emotional TTS framework with a novel approach for emotion intensity modeling to facilitate fine-grained control over emotion rendering at the phoneme, word, and utterance levels. We introduce a hierarchical emotion distribution (ED) extractor that captures a quantifiable ED embedding across different speech segment levels. Additionally, we explore various acoustic features and assess their impact on emotion intensity modeling. During TTS training, the hierarchical ED embedding effectively captures the variance in emotion intensity from the reference audio and correlates it with linguistic and speaker information. The TTS model not only generates emotional speech during inference, but also quantitatively controls the emotion rendering over the speech constituents. Both objective and subjective evaluations demonstrate the effectiveness of our framework in terms of speech quality, emotional expressiveness, and hierarchical emotion control.

The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow zero-shot speaker adaptation through auto-regressive (AR) continuation of acoustic tokens extracted from a short speech prompt. However, these AR models are restricted to generate speech only in a left-to-right direction, making them unsuitable for speech editing where both preceding and following contexts are provided. Furthermore, these models rely on acoustic tokens, which have audio quality limitations imposed by the performance of audio codec models. In this study, we propose a unified context-aware TTS framework called UniCATS, which is capable of both speech continuation and editing. UniCATS comprises two components, an acoustic model CTX-txt2vec and a vocoder CTX-vec2wav. CTX-txt2vec employs contextual VQ-diffusion to predict semantic tokens from the input text, enabling it to incorporate the semantic context and maintain seamless concatenation with the surrounding context. Following that, CTX-vec2wav utilizes contextual vocoding to convert these semantic tokens into waveforms, taking into consideration the acoustic context. Our experimental results demonstrate that CTX-vec2wav outperforms HifiGAN and AudioLM in terms of speech resynthesis from semantic tokens. Moreover, we show that UniCATS achieves state-of-the-art performance in both speech continuation and editing. Audio samples are available at https://cpdu.github.io/unicats.

Speaker verification encounters significant challenges when confronted with diverse domain data, often resulting in performance degradation due to domain mismatch. To enhance performance in cross-domain scenarios, we introduce the Domain Adapter, an adaptable module designed for specific domains. This module learns and integrates domain-specific information with speaker-related data, mitigating domain-related variations and promoting convergence of utterance embeddings from the same speaker across diverse domains. It offers configurability across multiple levels and is adaptable to various backbone architectures. Our proposed module substantially enhances cross-domain performance with minimal parameter increments while effectively generalizing to previously unseen domains. In our experiments, we present results on the 3D-Speaker dataset, which provides acoustically-relevant attributes crucial for domain categorization and the subsequent learning of domain information. The top-performing system integrated with domain adapters achieved 10.8%, 14.8%, and 21.1% EER improvements over the baseline across three 3D-Speaker dataset trials.

It remains a challenge to effectively control the emotion rendering in text-to-speech (TTS) synthesis. Prior studies have primarily focused on learning a global prosodic representation at the utterance level, which strongly correlates with linguistic prosody. Our goal is to construct a hierarchical emotion distribution (ED) that effectively encapsulates intensity variations of emotions at various levels of granularity, encompassing phonemes, words, and utterances. During TTS training, the hierarchical ED is extracted from the ground-truth audio and guides the predictor to establish a connection between emotional and linguistic prosody. At run-time inference, the TTS model generates emotional speech and, at the same time, provides quantitative control of emotion over the speech constituents. Both objective and subjective evaluations validate the effectiveness of the proposed framework in terms of emotion prediction and control.

Target speaker extraction aims to extract the speech of a specific speaker from a multi-talker mixture as specified by an auxiliary reference. Most studies focus on the scenario where the target speech is highly overlapped with the interfering speech. However, this scenario only accounts for a small percentage of real-world conversations. In this paper, we aim at the sparsely overlapped scenarios in which the auxiliary reference needs to perform two tasks simultaneously: detect the activity of the target speaker and disentangle the active speech from any interfering speech. We propose an audio-visual speaker extraction model named ActiveExtract, which leverages speaking activity from audio-visual active speaker detection (ASD). The ASD directly provides the frame-level activity of the target speaker, while its intermediate feature representation is trained to discriminate speech-lip synchronization that could be used for speaker disentanglement. Experimental results show our model outperforms baselines across various overlapping ratios, achieving an average improvement of more than 4 dB in terms of SI-SNR.

Voice conversion is becoming increasingly popular, and a growing number of application scenarios require models with streaming inference capabilities. The recently proposed DualVC attempts to achieve this objective through streaming model architecture design and intra-model knowledge distillation along with hybrid predictive coding to compensate for the lack of future information. However, DualVC encounters several problems that limit its performance. First, the autoregressive decoder has error accumulation in its nature and limits the inference speed as well. Second, the causal convolution enables streaming capability but cannot sufficiently use future information within chunks. Third, the model is unable to effectively address the noise in the unvoiced segments, lowering the sound quality. In this paper, we propose DualVC 2 to address these issues. Specifically, the model backbone is migrated to a Conformer-based architecture, empowering parallel inference. Causal convolution is replaced by non-causal convolution with a dynamic chunk mask to make better use of within-chunk future information. Also, quiet attention is introduced to enhance the model’s noise robustness. Experiments show that DualVC 2 outperforms DualVC and other baseline systems in both subjective and objective metrics, with only 186.4 ms latency. Our audio samples are made publicly available1.

Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned high-level features to the downstream speaker recognition task. However, this approach introduces extra parameters as the pretrained model remains in the inference stage. Another group of researchers directly apply self-supervised methods such as DINO to speaker embedding learning, yet they have not explored its potential on large-scale in-the-wild datasets. In this paper, we present the effectiveness of DINO training on the large-scale WenetSpeech dataset and its transferability in enhancing the supervised system performance on the CNCeleb dataset. Additionally, we introduce a confidence-based data filtering algorithm to remove unreliable data from the pretraining dataset, leading to better performance with less training data. The associated pretrained models, confidence files, pretraining and finetuning scripts will be made available in the Wespeaker toolkit.

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community remains constrained. One reason for this limitation is that a considerable amount of the publicly available speech data is compromised by background noise, speech overlapping, lack of speech segmentation information, missing speaker labels, and incomplete transcriptions, which can largely hinder their usefulness. On the other hand, human annotation of speech data is both time-consuming and costly. To address this issue, we introduce an automatic in-the-wild speech data preprocessing framework (AutoPrep) in this paper, which is designed to enhance speech quality, generate speaker labels, and produce transcriptions automatically. The proposed AutoPrep framework comprises six components: speech enhancement, speech segmentation, speaker clustering, target speech extraction, quality filtering and automatic speech recognition. Experiments conducted on the open-sourced WenetSpeech and our self-collected AutoPrepWild corpora demonstrate that the proposed AutoPrep framework can generate preprocessed data with similar DNSMOS and PDNSMOS scores compared to several open-sourced TTS datasets. The corresponding TTS system can achieve up to 0.68 in-domain speaker similarity.1

Voice conversion (VC) aims to modify the speaker’s timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system’s capability to preserve source speech prosody, as validated on the Emotional Speech Database.

The variety of spoofing algorithms used in generating speech poses obstacles to fake speech detection. Earlier methods have demonstrated complementary effects for detection. This paper proposes a novel hierarchical multi-path multi-model selection method for fake speech detection. It is designed to dynamically select and utilise the most suitable model from a set of complementary models. In our method, four basic detection models are incorporated, each offering partial but complementary detection abilities, to enhance balanced performance on diverse fake speech. The models are trained through a multi-path schema and the selection mechanism is structured hierarchically to improve the generalisation ability. Our method achieves an Equal Error Rate (EER) of 0.37% on the ASVspoof 2019 LA dataset, and outperforms other state-of-the-art method on the cross-domain and cross-dataset scenarios. A statistical analysis of EERs against thirteen unknown attacks reveals our method’s superiority, evidenced by the lowest standard deviation of 0.24, further underscoring our method’s robustness against a range of attacks.

Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a commonly adopted technique. Unlike typical data augmentation applied to speech mixtures, this work thoroughly investigates the effectiveness of augmenting the enrollment speech space. We found that for both pretrained and jointly optimized speaker encoders, directly augmenting the enrollment speech leads to consistent performance improvement. In addition to conventional methods such as noise and reverberation addition, we propose a novel augmentation method called self-estimated speech augmentation (SSA). Experimental results on the Libri2Mix test set show that our proposed method can achieve an improvement of up to 2.5 dB.

Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and repeating due to the lack of explicit monotonic alignment constraints. In this paper, we notice from the attention maps that some particular attention heads of the decoder-only model indicate the alignments between speech and text. We call the attention maps of those heads Alignment-Emerged Attention Maps (AEAMs). Based on this discovery, we propose a novel inference method without altering the training process, named Attention-Constrained Inference (ACI), to facilitate monotonic synthesis. It first identifies AEAMs using the Attention Sweeping algorithm and then applies constraining masks on AEAMs. Our experimental results on decoderonly TTS model VALL-E show that the WER of synthesized speech is reduced by up to 20.5% relatively with ACI while the naturalness and speaker similarity are comparable.

Target Speaker Extraction (TSE) aims to extract target speech from mixed audio using clues that identify the target speaker. However, TSE often faces the Target Confusion (TC) problem, where the model extracts the interfering speech instead of the target speech, leading to significant performance degradation. In this paper, we propose a novel model with two branches that enhance target speech extraction by explicitly modeling the interference. Additionally, we propose a Target Confusion Rectification (TCR) method to address the aforementioned TC problem. When the TSE model outputs the wrong speaker, the TCR method performs a rectifying step to ensure the model extracts the correct speaker. Experiments show that under the train-100 subset of Libri2Mix dataset, our proposed method significantly improves the extracting performance in terms of SI-SNRi, PESQ score and extracting accuracy, with that under ‘mix_clean’ subset slightly better than that under ‘mix_both’ subset.

Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For evaluation, we propose an iterative decoding method that outputs diarization results for each speaker sequentially. Additionally, we propose an Enhancer module to enhance the frame-level speaker embeddings, enabling the model to handle scenarios with an unseen number of speakers. We also explore replacing the transformer encoder with a Conformer architecture, which better models local information. Furthermore, we discovered that commonly used simulation datasets for speaker diarization have a much higher overlap ratio compared to real data. We found that using simulated training data that is more consistent with real data can achieve an improvement in consistency. Extensive experimental validation demonstrates the effectiveness of our proposed methodologies. Our best system achieved a new state-of-the-art diarization error rate (DER) performance on all the CALLHOME (10.08%), DIHARD II (24.64%), and AMI (13.00%) evaluation benchmarks when overlap is considered and no oracle voice activity detection (VAD) is used. Beyond speaker diarization, our AED-EEND system also shows remarkable competitiveness as a speech type detection model.

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition, speaker diarization, speech synthesis, and target speaker extraction. In this overview, we present a comprehensive review of neural approaches to speaker representation learning from both theoretical and practical perspectives. Theoretically, we discuss speaker encoders ranging from supervised to self-supervised learning algorithms, standalone models to large pretrained models, pure speaker embedding learning to joint optimization with downstream tasks, and efforts toward interpretability. Practically, we systematically examine approaches for robustness and effectiveness, introduce and compare various open-source toolkits in the field. Through the systematic and comprehensive review of the relevant literature, research activities, and resources, we provide a clear reference for researchers in the speaker characterization and modeling field, as well as for those who wish to apply speaker modeling techniques to specific downstream tasks.

Speech separation seeks to separate individual speech signals from a speech mixture. Typically, most separation models are trained on synthetic data due to the unavailability of target reference in real-world cocktail party scenarios. As a result, there exists a domain gap between real and synthetic data when deploying speech separation models in real-world applications. In this paper, we propose a self-supervised domain-invariant pretrained (DIP) frontend that is exposed to mixture data without the need for target reference speech. The DIP frontend utilizes a Siamese network with two innovative pretext tasks, mixture predictive coding (MPC) and mixture invariant coding (MIC), to capture shared contextual cues between real and synthetic unlabeled mixtures. Subsequently, we freeze the DIP frontend as a feature extractor when training the downstream speech separation models on synthetic data. By pretraining the DIP frontend with the contextual cues, we expect that the speech separation skills learned from synthetic data can be effectively transferred to real data. To benefit from the DIP frontend, we introduce a novel separation pipeline to align the feature resolution of the separation models. We evaluate the speech separation quality on standard benchmarks and real-world datasets. The results confirm the superiority of our DIP frontend over existing speech separation models. This study underscores the potential of large-scale pretraining to enhance the quality and intelligibility of speech separation in real-world applications.

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.

Nowadays, recognition-synthesis-based methods have been quite popular with voice conversion (VC). By introducing linguistics features with good disentangling characters extracted from an automatic speech recognition (ASR) model, the VC performance achieved considerable breakthroughs. Recently, self-supervised learning (SSL) methods trained with a large-scale unannotated speech corpus have been applied to downstream tasks focusing on the content information, which is suitable for VC tasks. However, a huge amount of speaker information in SSL representations degrades timbre similarity and the quality of converted speech significantly. To address this problem, we proposed a high-similarity any-to-one voice conversion method with the input of SSL representations. We incorporated adversarial training mechanisms in the synthesis module using external unannotated corpora. Two auxiliary discriminators were trained to distinguish whether a sequence of mel-spectrograms has been converted by the acoustic model and whether a sequence of content embeddings contains speaker information from external corpora. Experimental results show that our proposed method achieves comparable similarity and higher naturalness than the supervised method, which needs a huge amount of annotated corpora for training and is applicable to improve similarity for VC methods with other SSL representations as input.

The majority of modern speaker verification systems take spectral analysis-based features as input, which contains multiple frequency bins. Naturally, there would be a question of whether all different frequency bins contribute equally to the speaker verification system performance? In this paper, we propose the frequency reweighting layer (FRL) to automatically learn and balance the importance of different frequency bins. This new layer can be freely inserted into the original speaker embedding learner once or multiple times at different layers, with an ignorable number of new parameters. Based on the proposed novel architecture, a set of experiments are designed and carried out on the VoxCeleb1 dataset, which not only achieves superior performance but also exhibits an interesting weight distribution – the lower frequencies matter more.

As the most widely used technique, deep speaker embedding learning has become predominant in speaker verification task recently. Very large neural networks such as ECAPA-TDNN and ResNet can achieve the state-of-the-art performance. However, large models are computationally unfriendly in general, which require massive storage and computation resources. Model compression has been a hot research topic. Parameter quantization usually results in significant performance degradation. Knowledge distillation demands a pretrained complex teacher model. In this paper, we introduce a novel self-knowledge distillation method, namely Self-Knowledge Distillation via Feature Enhancement (SKDFE). It utilizes an auxiliary self-teacher network to distill its own refined knowledge without the need of a pretrained teacher network. Additionally, we apply the self-knowledge distillation at two different levels: label level and feature level. Experiments on Voxceleb dataset show that our proposed self-knowledge distillation method can make small models have comparable or even better performance than large ones. Large models can also be further improved when applying our method.

Large performance degradation is often observed for speaker verification systems when applied to a new domain dataset. Given an unlabeled target-domain dataset, unsupervised domain adaptation (UDA) methods, which usually leverage adversarial training strategies, are commonly used to bridge the performance gap caused by the domain mismatch. However, such adversarial training strategy only uses the distribution information of target domain data and can not ensure the performance improvement on the target domain. In this paper, we incorporate self-supervised learning strategy to the unsupervised domain adaptation system and proposed a self-supervised learning based domain adaptation approach (SSDA). Compared to the traditional UDA method, the new SSDA training strategy can fully leverage the potential label information from target domain and adapt the speaker discrimination ability from source domain simultaneously. We evaluated the proposed approach on the Vox-Celeb (labeled source domain) and CnCeleb (unlabeled target domain) datasets, and the best SSDA system obtains 10.2% Equal Error Rate (EER) on the CnCeleb dataset without using any speaker labels on CnCeleb, which also can achieve the state-of-the-art results on this corpus.

Text-dependent speaker verification systems trained on large amount of labelled data exhibit remarkable performance. However, collecting the speech from a lot of speakers with target transcript is a lengthy and expensive process. In this work, we propose a synthesis based data augmentation method (SynAug) to expand the training set with more speakers and text-controlled synthesized speech. The performance of SynAug is evaluated on the RSR2015 dataset. Experimental results show that for i-vector framework, the proposed methods can boost the system performance significantly, especially for the low-resource condition where the amount of genuine speech is extremely limited. Moreover, combined with traditional data augmentation methods such as adding noises and reverberation, the systems could be further strengthened in extremely limited resource situation.

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the lexicon variation neglected. For text dependent speaker verification tasks, it’s well-known that preparing training data with the target transcript is the most effectual approach to build a well-performing system, however collecting such data is time-consuming and expensive. In this work, we propose a unit selection synthesis based data augmentation method to leverage the abundant text-independent data resources. In this approach text-independent speeches of each speaker are firstly broke up to speech segments each contains one phone unit. Then segments that contain phonetics in the target transcript are selected to produce a speech with the target transcript by concatenating them in turn. Experiments are carried out on the AISHELL Speaker Verification Challenge 2019 database, the results and analysis shows that our proposed method can boost the system performance significantly.

Voice activity detection is an essential pre-processing component for speech-related tasks such as automatic speech recognition (ASR). Traditional supervised VAD systems obtain frame-level labels from an ASR pipeline by using, e.g., a Hidden Markov model. These ASR models are commonly trained on clean and fully transcribed data, limiting VAD systems to be trained on clean or synthetically noised datasets. Therefore, a major challenge for supervised VAD systems is their generalization towards noisy, real-world data. This work proposes a data-driven teacher-student approach for VAD, which utilizes vast and unconstrained audio data for training. Unlike previous approaches, only weak labels during teacher training are required, enabling the utilization of any real-world, potentially noisy dataset. Our approach firstly trains a teacher model on a source dataset (Audioset) using clip-level supervision. After training, the teacher provides frame-level guidance to a student model on an unlabeled, target dataset. A multitude of student models trained on mid- to large-sized datasets are investigated (Audioset, Voxceleb, NIST SRE). Our approach is then respectively evaluated on clean, artificially noised, and real-world data. We observe significant performance gains in artificially noised and real-world scenarios. Lastly, we compare our approach against other unsupervised and supervised VAD methods, demonstrating our method's superiority.

Voice and face are two most popular biometrics for person verification, usually used in speaker verification and face verification tasks. It has already been observed that simply combining the information from these two modalities can lead to a more powerful and robust person verification system. In this article, to fully explore the multi-modal learning strategies for person verification, we proposed three types of audio-visual deep neural network (AVN), including feature level AVN (AVN-F), embedding level AVN (AVN-E), and embedding level combination with joint learning AVN (AVN-J). To further enhance the system robustness in real noisy conditions where not both modalities can be accessed with high-quality, we proposed several data augmentation strategies for each proposed AVN: A feature-level multi-modal data augmentation is proposed for AVN-F and an embedding-level data augmentation with novel noise distribution matching is designed for AVN-E. For AVN-J, both the feature and embedding level multi-modal data augmentation methods can be applied. All the proposed models are trained on the VoxCeleb2 dev dataset and evaluated on the standard VoxCeleb1 dataset, and the best system achieves 0.558, 0.441% and 0.793% EER on the three official trial lists of VoxCeleb1, which is to our knowledge the best published single system results on this corpus for person verification. To validate the robustness of the proposed approaches, a noisy evaluation set based on the VoxCeleb1 is constructed, and experimental results show that the proposed system can significantly boost the system robustness and still show promising performance under this noisy scenario.

SpecAugment is a newly proposed data augmentation method for speech recognition. By randomly masking bands in the log Mel spectogram this method leads to impressive performance improvements. In this paper, we investigate the usage of SpecAugment for speaker verification tasks. Two different models, namely 1-D convolutional TDNN and 2-D convolutional ResNet34, trained with either Softmax or AAM-Softmax loss, are used to analyze SpecAugment's effectiveness. Experiments are carried out on the Voxceleb and NIST SRE 2016 dataset. By applying SpecAugment to the original clean data in an on-the-fly manner without complex off-line data augmentation methods, we obtained 3.72% and 11.49% EER for NIST SRE 2016 Cantonese and Tagalog, respectively. For Voxceleb1 evaluation set, we obtained 1.47% EER.

Using deep neural network to extract speaker embedding has significantly improved the speaker verification task. However, such embeddings are still vulnerable to channel variability. Previous works have used adversarial training to suppress channel information to extract channel-invariant embedding and achieved a significant improvement. Inspired by the successful joint multi-task and adversarial training with phonetic information for phonetic-invariant speaker embedding learning, in this paper, a similar methodology is developed to suppress the channel variability. By treating the recording devices or environments as the channel variability, two individual experiments are carried out, and consistent performance improvement is observed in both cases. The best performance is obtained by sequentially applying multi-task training at the statistics pooling layer and adversarial training at the embedding layer, achieving 10.77% and 9.37% relative improvements in terms of EER compared to the baselines, for the recording environments or devices level, respectively.

This paper presents an analysis of our diarization system winning the second DIHARD speech diarization challenge, track 1. This system is based on clustering x-vector speaker embeddings extracted every 0.25s from short segments of the input recording. In this paper, we focus on the two x-vector clustering methods employed, namely Agglomerative Hierarchical Clustering followed by a clustering based on Bayesian Hidden Markov Model (BHMM). Even though the system submitted to the challenge had further post-processing steps, we will show that using this BHMM solely is enough to achieve the best performance in the challenge. The analysis will show improvements achieved by optimizing individual processing steps, including a simple procedure to effectively perform "domain adaptation" by Probabilistic Linear Discriminant Analysis model interpolation. All experiments are performed in the DIHARD II evaluation framework.

This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2 the systems were mainly based on performing agglomerative hierarchical clustering (AHC) of x-vectors, followed by another x-vector clustering based on Bayes hidden Markov model and variational Bayes inference. We provide a comparison of the improvement given by each step and share the implementation of the core of the system. For tracks 3 and 4 with recordings from the Fifth CHiME Challenge, we explored different approaches for doing multi-channel diarization and our best performance was obtained when applying AHC on the fusion of per channel probabilistic linear discriminant analysis scores.

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully collecting data with the target speech content, such data collection could be costly and inflexible. In this paper, we propose a novel text adaptation framework to address the text mismatch issue. Here, a speaker-text factorization network is proposed to factorize the input speech into speaker embeddings and text embeddings and then integrate them into a single representation in the later stage. Given a small amount of speaker-independent adaptation utterances, text embeddings of target speech content can be extracted and used to adapt the text-independent speaker embeddings to text-customized speaker embeddings. Experiments on RSR2015 show that text adaptation can significantly improve the performance of text mismatch conditions.

Data augmentation is an effective method to improve the robustness of embedding based speaker verification systems, which could be applied to either the front-end speaker embedding extractor or the back-end PLDA. Different from the conventional augmentation methods such as manually adding noise or reverberation to the original audios, in this article, we propose to use deep generative models to directly generate more diverse speaker embeddings, which would be used for robust PLDA training. Conditional GAN, and VAE are designed, and investigated for different embedding types, including factor analysis based i-vector, TDNN based x-vector, and ResNet based r-vector. The proposed back-end augmentation methods are evaluated on NIST SRE 2016, and 2018 dataset. Within the popular x-vector, and r-vector framework, the experimental results show that our proposed methods can outperform the traditional audio based back-end augmentation method while different front-end augmentation methods are considered.

Deep speaker embedding learning is an effective method for speaker identity modelling. Very deep models such as ResNet can achieve remarkable results but are usually too computationally expensive for real applications with limited resources. On the other hand, simply reducing model size is likely to result in significant performance degradation. In this paper, label-level and embedding-level knowledge distillation are proposed to narrow down the performance gap between large and small models. Label-level distillation utilizes the posteriors obtained by a well-trained teacher model to guide the optimization of the student model, while embedding-level distillation directly constrains the similarity between embeddings learned by two models. Experiments were carried out on the VoxCeleb1 dataset. Results show that the proposed knowledge distillation methods can significantly boost the performance of highly compact student models.

In the original version of this article, there is a mistake about the result of DPCL++ (Isik et al., 2016) in Section 5.6 (Fig. 7). As reported in Isik et al. (2016), the SDR improvement was 10.3 dB, rather than 9.4 dB. For further information, the best performance in Isik et al. (2016) was 10.8 dB with the help of a more complicated architecture.

Short duration text-independent speaker verification remains a hot research topic in recent years, and deep neural network based embeddings have shown impressive results in such conditions. Good speaker embeddings require the property of both small intra-class variation and large inter-class difference, which is critical for the ability of discrimination and generalization. Current embedding learning strategies can be grouped into two frameworks: “Cascade embedding learning” with multiple stages and “direct embedding learning” from spectral feature directly. We propose new approaches to achieve more discriminant speaker embeddings. Within the cascade framework, a neural network based deep discriminant analysis (DDA) is proposed to project i-vector to more discriminative embeddings. Within the direct embedding framework, a deep model with more advanced center loss and A-softmax loss is used, the focal loss is also investigated in this framework. Moreover, the traditional i-vector and neural embeddings are finally combined with neural network based DDA to achieve further gain. Main experiments are carried out on a short-duration text-independent speaker verification dataset generated from the SRE corpus. The results show that the newly proposed method is promising for short-duration text-independent speaker verification, and it is consistently better than traditional i-vector and neural embedding baselines. The best embeddings achieve roughly 30% relative EER reduction compared to the i-vector baseline, which could be further enhanced when combined with the i-vector system.

Factor analysis based i-vector has been the state-of-the-art method for speaker verification. Recently, researchers propose to build DNN based end-to-end speaker verification systems and achieve comparable performance withi-vector. Since these two methods possess their own property and differ from each other significantly, we explore a framework to integrate these two paradigms together to utilize their complementarity. More specifically, in this paper we develop and compare four methodologies to integrate traditionali-vector into end-to-end systems, including score fusion, embeddings concatenation, transformed concatenation and joint learning. All these approaches achieve significant gains. Moreover, the hard trial selection is performed on the end-to-end architecture which further improves the performance. Experimental results on a text-independent short-duration dataset generated from SRE 2010 reveal that the newly proposed method reduces the EER by relative 31.0% and 28.2% compared to the i-vector and end-to-end baselines respectively.

Recognizing the identities of multiple talkers via their overlapped speech is a challenging task, it is also one main difficulty for the “cocktail party problem”. In this paper, a novel dilated convolutional neural network with a focal KL-divergence loss function is proposed to tackle this problem. During training, relative loss for the well-classified samples is automatically reduced and consequently more attention is paid to the hard samples. The use of the focal KL-divergence loss function leads to more stable training and improved testing performance. Furthermore, a post processing of assigning different frames with different weights is also adopted and leads to further improvement. The proposed framework can be easily extended from 2-talker to 3-talker speaker identification scenario. Experiments on the artificially generated RSR2015 multi-talker mixed corpus show that the proposed approach can improve multi-talker speaker identification significantly.

The cocktail party problem, i.e., tracing and recognizing the speech of a specific speaker when multiple speakers talk simultaneously, is one of the critical problems yet to be solved to enable the wide application of automatic speech recognition (ASR) systems. In this overview paper, we review the techniques proposed in the last two decades in attacking this problem. We focus our discussions on the speech separation problem given its central role in the cocktail party environment, and describe the conventional single-channel techniques such as computational auditory scene analysis (CASA), non-negative matrix factorization (NMF) and generative models, the conventional multi-channel techniques such as beamforming and multi-channel blind source separation, and the newly developed deep learning-based techniques, such as deep clustering (DPCL), the deep attractor network (DANet), and permutation invariant training (PIT). We also present techniques developed to improve ASR accuracy and speaker identification in the cocktail party environment. We argue effectively exploiting information in the microphone array, the acoustic training set, and the language itself using a more powerful model. Better optimization objective and techniques will be the approach to solving the cocktail party problem.

In the original version of this article, the affiliations are incorrect. The correct affiliations are given above. The corresponding author’s E-mail address should be [email protected].

A water drop behaves differently from a large water body because of its strong viscosity and surface tension under the small scale. Surface tension causes the motion of a water drop to be largely determined by its boundary surface. Meanwhile, viscosity makes the interior of a water drop less relevant to its motion, as the smooth velocity field can be well approximated by an interpolation of the velocity on the boundary. Consequently, we propose a fast deformable surface model to realistically animate water drops and their flowing behaviors on solid surfaces. Our system efficiently simulates water drop motions in a Lagrangian fashion, by reducing 3D fluid dynamics over the whole liquid volume to a deformable surface model. In each time step, the model uses an implicit mean curvature flow operator to produce surface tension effects, a contact angle operator to change droplet shapes on solid surfaces, and a set of mesh connectivity updates to handle topological changes and improve mesh quality over time. Our numerical experiments demonstrate a variety of physically plausible water drop phenomena at a real-time rate, including capillary waves when water drops collide, pinch-off of water jets, and droplets flowing over solid materials. The whole system performs orders-of-magnitude faster than existing simulation approaches that generate comparable water drop effects.