Search

Empathetic dialogue is crucial for natural human-computer interaction, allowing the dialogue system to respond in a more personalized and emotionally aware manner, improving user satisfaction and engagement. The emergence of large language models (LLMs) has revolutionized dialogue generation by harnessing their powerful capabilities and shown its potential in multimodal domains. Many studies have integrated speech with text-based LLMs to take speech question as input and output text response. However, the lack of spoken question-answering datasets that include speech style information to supervised fine-tuning (SFT) limits the performance of these systems. As a result, while these systems excel at understanding speech content, they often struggle to generate empathetic responses. In response, we propose a novel approach that circumvents the need for question-answering data, called Listen, Perceive, and Express (LPE). Our method employs a two-stage training process, initially guiding the LLM to listen the content and perceive the emotional aspects of speech. Subsequently, we utilize Chain-of-Thought (CoT) prompting to unlock the model's potential for expressing empathetic responses based on listened spoken content and perceived emotional cues. We employ experiments to prove the effectiveness of proposed method. To our knowledge, this is the first attempt to leverage CoT for speech-based dialogue., Comment: Accepted by ICASSP 2025

Early detection of neurocognitive disorders (NCDs) is crucial for timely intervention and disease management. Speech analysis offers a non-intrusive and scalable screening method, particularly through narrative tasks in neuropsychological assessment tools. Traditional narrative analysis often focuses on local indicators in microstructure, such as word usage and syntax. While these features provide insights into language production abilities, they often fail to capture global narrative patterns, or microstructures. Macrostructures include coherence, thematic organization, and logical progressions, reflecting essential cognitive skills potentially critical for recognizing NCDs. Addressing this gap, we propose to investigate specific cognitive and linguistic challenges by analyzing topical shifts, temporal dynamics, and the coherence of narratives over time, aiming to reveal cognitive deficits by identifying narrative impairments, and exploring their impact on communication and cognition. The investigation is based on the CU-MARVEL Rabbit Story corpus, which comprises recordings of a story-telling task from 758 older adults. We developed two approaches: the Dynamic Topic Models (DTM)-based temporal analysis to examine the evolution of topics over time, and the Text-Image Temporal Alignment Network (TITAN) to evaluate the coherence between spoken narratives and visual stimuli. DTM-based approach validated the effectiveness of dynamic topic consistency as a macrostructural metric (F1=0.61, AUC=0.78). The TITAN approach achieved the highest performance (F1=0.72, AUC=0.81), surpassing established microstructural and macrostructural feature sets. Cross-comparison and regression tasks further demonstrated the effectiveness of proposed dynamic macrostructural modeling approaches for NCD detection., Comment: 12 pages, 8 figures

Controlling text-to-speech (TTS) systems to synthesize speech with the prosodic characteristics expected by users has attracted much attention. To achieve controllability, current studies focus on two main directions: (1) using reference speech as prosody prompt to guide speech synthesis, and (2) using natural language descriptions to control the generation process. However, finding reference speech that exactly contains the prosody that users want to synthesize takes a lot of effort. Description-based guidance in TTS systems can only determine the overall prosody, which has difficulty in achieving fine-grained prosody control over the synthesized speech. In this paper, we propose DrawSpeech, a sketch-conditioned diffusion model capable of generating speech based on any prosody sketches drawn by users. Specifically, the prosody sketches are fed to DrawSpeech to provide a rough indication of the expected prosody trends. DrawSpeech then recovers the detailed pitch and energy contours based on the coarse sketches and synthesizes the desired speech. Experimental results show that DrawSpeech can generate speech with a wide variety of prosody and can precisely control the fine-grained prosody in a user-friendly manner. Our implementation and audio samples are publicly available., Comment: Accepted by ICASSP 2025

Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the pronunciation of a polyphonic character, which accepts sentence containing polyphonic character as input in the form of Chinese character sequence without the necessity of any preprocessing. The proposed method consists of a pre-trained bidirectional encoder representations from Transformers (BERT) model and a neural network (NN) based classifier. The pre-trained BERT model extracts semantic features from a raw Chinese character sequence and the NN based classifier predicts the polyphonic character's pronunciation according to BERT output. In out experiments, we implemented three classifiers, a fully-connected network based classifier, a long short-term memory (LSTM) network based classifier and a Transformer block based classifier. The experimental results compared with the baseline approach based on LSTM demonstrate that, the pre-trained model extracts effective semantic features, which greatly enhances the performance of polyphone disambiguation. In addition, we also explored the impact of contextual information on polyphone disambiguation., Comment: Accepted at INTERSPEECH 2019

Identifying the emotional state from speech is essential for the natural interaction of the machine with the speaker. However, extracting effective features for emotion recognition is difficult, as emotions are ambiguous. We propose a novel approach to learn discriminative features from variable length spectrograms for emotion recognition by cooperating softmax cross-entropy loss and center loss together. The softmax cross-entropy loss enables features from different emotion categories separable, and center loss efficiently pulls the features belonging to the same emotion category to their center. By combining the two losses together, the discriminative power will be highly enhanced, which leads to network learning more effective features for emotion recognition. As demonstrated by the experimental results, after introducing center loss, both the unweighted accuracy and weighted accuracy are improved by over 3\% on Mel-spectrogram input, and more than 4\% on Short Time Fourier Transform spectrogram input., Comment: Accepted at ICASSP 2019

Alzheimer's Disease (AD) detection has emerged as a promising research area that employs machine learning classification models to distinguish between individuals with AD and those without. Unlike conventional classification tasks, we identify within-class variation as a critical challenge in AD detection: individuals with AD exhibit a spectrum of cognitive impairments. Given that many AD detection tasks lack fine-grained labels, simplistic binary classification may overlook two crucial aspects: within-class differences and instance-level imbalance. The former compels the model to map AD samples with varying degrees of impairment to a single diagnostic label, disregarding certain changes in cognitive function. While the latter biases the model towards overrepresented severity levels. This work presents early efforts to address these challenges. We propose two novel methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe), targeting two problems respectively. Experiments on the ADReSS and ADReSSo datasets demonstrate that the proposed methods significantly improve detection accuracy. Further analysis reveals that SoTD effectively harnesses the strengths of multiple component models, while InRe substantially alleviates model over-fitting. These findings provide insights for developing more robust and reliable AD detection models.

Current Text-to-audio (TTA) models mainly use coarse text descriptions as inputs to generate audio, which hinders models from generating audio with fine-grained control of content and style. Some studies try to improve the granularity by incorporating additional frame-level conditions or control networks. However, this usually leads to complex system design and difficulties due to the requirement for reference frame-level conditions. To address these challenges, we propose AudioComposer, a novel TTA generation framework that relies solely on natural language descriptions (NLDs) to provide both content specification and style control information. To further enhance audio generative modeling, we employ flow-based diffusion transformers with the cross-attention mechanism to incorporate text descriptions effectively into audio generation processes, which can not only simultaneously consider the content and style information in the text inputs, but also accelerate generation compared to other architectures. Furthermore, we propose a novel and comprehensive automatic data simulation pipeline to construct data with fine-grained text descriptions, which significantly alleviates the problem of data scarcity in the area. Experiments demonstrate the effectiveness of our framework using solely NLDs as inputs for content specification and style control. The generation quality and controllability surpass state-of-the-art TTA models, even with a smaller model size.

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and transcribing overlapping speech. To address these challenges, this paper investigates the role of Connectionist Temporal Classification (CTC) in speaker disentanglement when incorporated with Serialized Output Training (SOT) for MTASR. Our visualization reveals that CTC guides the encoder to represent different speakers in distinct temporal regions of acoustic embeddings. Leveraging this insight, we propose a novel Speaker-Aware CTC (SACTC) training objective, based on the Bayes risk CTC framework. SACTC is a tailored CTC variant for multi-talker scenarios, it explicitly models speaker disentanglement by constraining the encoder to represent different speakers' tokens at specific time frames. When integrated with SOT, the SOT-SACTC model consistently outperforms standard SOT-CTC across various degrees of speech overlap. Specifically, we observe relative word error rate reductions of 10% overall and 15% on low-overlap speech. This work represents an initial exploration of CTC-based enhancements for MTASR tasks, offering a new perspective on speaker disentanglement in multi-talker speech recognition. The code is available at https://github.com/kjw11/Speaker-Aware-CTC., Comment: Accepted by ICASSP2025

The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale, often producing unnatural or even unintelligible speech. This work proposes CoFi-Speech, a coarse-to-fine CLM-TTS approach, employing multi-scale speech coding and generation to address this issue. We train a multi-scale neural codec, CoFi-Codec, to encode speech into a multi-scale discrete representation, comprising multiple token sequences with different time resolutions. Then, we propose CoFi-LM that can generate this representation in two modes: the single-LM-based chain-of-scale generation and the multiple-LM-based stack-of-scale generation. In experiments, CoFi-Speech significantly outperforms single-scale baseline systems on naturalness and speaker similarity in zero-shot TTS. The analysis of multi-scale coding demonstrates the effectiveness of CoFi-Codec in learning multi-scale discrete speech representations while keeping high-quality speech reconstruction. The coarse-to-fine multi-scale generation, especially for the stack-of-scale approach, is also validated as a crucial approach in pursuing a high-quality neural codec language model for TTS.

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spoken. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. These representations are then fed into an LLM fine-tuned using LoRA, enabling the capabilities for speech comprehension and transcription. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios, highlighting the potential of LLM to handle speech-related tasks based on user instructions in such complex settings.

The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It compresses speech into a shorter, multi-stream discrete semantic sequence with multiple tokens at each frame. Meanwhile, the ordered product quantization is proposed to constrain this sequence into an ordered representation. It can be applied with a multi-stream delayed LM to achieve better autoregressive generation along both time and stream axes in TTS. The experimental result strongly demonstrates the effectiveness of the proposed approach, achieving superior performance over baseline systems even if compressing the frameshift of speech from 20ms to 240ms (12x). The ablation studies further validate the importance of learning the proposed ordered multi-stream semantic representation in pursuing shorter speech sequences for efficient LM-based TTS., Comment: Accepted by SLT 2024

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (\textit{e.g.}, VALL-E) or Non-auto-regressive (NAR) based models (\textit{e.g.}, NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models need phoneme-level duration alignment information, thereby increasing the complexity of data pre-processing, model design, and loss design. In this work, we build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods, offering the following key advantages: (1) simplified data preparation; (2) straightforward model and loss design; and (3) stable, high-quality generation performance with fast inference speed. Compared to our previous publication, we present ({\romannumeral1}) a detailed analysis of the influence of speech tokenizer and noisy label for TTS performance; ({\romannumeral2}) four distinct types of sentence duration predictors; ({\romannumeral3}) a novel flow-based scalar latent transformer diffusion model. With these improvement, we show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models. Furthermore, we show that SimpleSpeech 2 can be seamlessly extended to multilingual TTS by training it on multilingual speech datasets. Demos are available on: {https://dongchaoyang.top/SimpleSpeech2\_demo/}., Comment: Submit to TASLP

Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained on large, diverse, and low-quality speech datasets, resulting in highly natural synthesized speech. However, they are limited by the difficulty of simulating various spontaneous behaviors and capturing prosody variations in spontaneous speech. In this paper, we propose a novel spontaneous speech synthesis system based on language models. We systematically categorize and uniformly model diverse spontaneous behaviors. Moreover, fine-grained prosody modeling is introduced to enhance the model's ability to capture subtle prosody variations in spontaneous speech.Experimental results show that our proposed method significantly outperforms the baseline methods in terms of prosody naturalness and spontaneous behavior naturalness., Comment: Accepted by INTERSPEECH 2024

Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this study, we propose a pioneering approach to empower Whisper, which is a speech foundation model, to tackle joint multi-talker and target-talker speech recognition tasks. Specifically, (i) we freeze Whisper and plug a Sidecar separator into its encoder to separate mixed embedding for multiple talkers; (ii) a Target Talker Identifier is introduced to identify the embedding flow of the target talker on the fly, requiring only three-second enrollment speech as a cue; (iii) soft prompt tuning for decoder is explored for better task adaptation. Our method outperforms previous methods on two- and three-talker LibriMix and LibriSpeechMix datasets for both tasks, and delivers acceptable zero-shot performance on multi-talker ASR on AishellMix Mandarin dataset., Comment: Accepted to INTERSPEECH 2024

We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector quantization, which are originally designed for audio compression and sacrifice fidelity compared to mel-spectrograms. Specifically, (i) instead of cross-entropy loss, we apply regression loss with a proposed spectrogram flux loss function to model the probability distribution of the continuous-valued tokens. (ii) we have incorporated variational inference into MELLE to facilitate sampling mechanisms, thereby enhancing the output diversity and model robustness. Experiments demonstrate that, compared to the two-stage codec language models VALL-E and its variants, the single-stage MELLE mitigates robustness issues by avoiding the inherent flaws of sampling discrete codes, achieves superior performance across multiple metrics, and, most importantly, offers a more streamlined paradigm. See https://aka.ms/melle for demos of our work.

Self-supervised (SSL) models have shown great performance in various downstream tasks. However, they are typically developed for limited languages, and may encounter new languages in real-world. Developing a SSL model for each new language is costly. Thus, it is vital to figure out how to efficiently adapt existed SSL models to a new language without impairing its original abilities. We propose adaptation methods which integrate LoRA to existed SSL models to extend new language. We also develop preservation strategies which include data combination and re-clustering to retain abilities on existed languages. Applied to mHuBERT, we investigate their effectiveness on speech re-synthesis task. Experiments show that our adaptation methods enable mHuBERT to be applied to a new language (Mandarin) with MOS value increased about 1.6 and the relative value of WER reduced up to 61.72%. Also, our preservation strategies ensure that the performance on both existed and new languages remains intact., Comment: Accepted by Interspeech 2024

The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high audio reconstruction quality. The key idea is to reduce the modality heterogeneity between text and audio by compressing the audio modality into a well-trained LLMs token space. Thus, the audio representation can be viewed as a new \textit{foreign language}, and LLMs can learn the new \textit{foreign language} with several demonstrations. In experiments, we investigate the performance of the proposed approach across multiple audio understanding and generation tasks, \textit{e.g.} speech emotion classification, audio classification, text-to-speech generation, speech enhancement, etc. The experimental results demonstrate that the LLMs equipped with the proposed LLM-Codec, named as UniAudio 1.5, prompted by only a few examples, can achieve the expected functions in simple scenarios. It validates the feasibility and effectiveness of the proposed cross-modal in-context learning approach. To facilitate research on few-shot audio task learning and multi-modal LLMs, we have open-sourced the LLM-Codec model.

Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural codec language modeling to improve the reconstruction results, especially for the speaker similarity and prosody naturalness. Our proposed model consists of: (i) a multi-modal content encoder to extract robust phoneme embeddings from dysarthric speech with auxiliary visual inputs; (ii) a speaker codec encoder to extract and normalize the speaker-aware codecs from the dysarthric speech, in order to provide original timbre and normal prosody; (iii) a codec language model based speech decoder to reconstruct the speech based on the extracted phoneme embeddings and normalized codecs. Evaluations on the commonly used UASpeech corpus show that our proposed model can achieve significant improvements in terms of speaker similarity and prosody naturalness., Comment: Accepted by Interspeech 2024

VQ-VAE, as a mainstream approach of speech tokenizer, has been troubled by ``index collapse'', where only a small number of codewords are activated in large codebooks. This work proposes product-quantized (PQ) VAE with more codebooks but fewer codewords to address this problem and build large-codebook speech tokenizers. It encodes speech features into multiple VQ subspaces and composes them into codewords in a larger codebook. Besides, to utilize each VQ subspace well, we also enhance PQ-VAE via a dual-decoding training strategy with the encoding and quantized sequences. The experimental results demonstrate that PQ-VAE addresses ``index collapse" effectively, especially for larger codebooks. The model with the proposed training strategy further improves codebook perplexity and reconstruction quality, outperforming other multi-codebook VQ approaches. Finally, PQ-VAE demonstrates its effectiveness in language-model-based TTS, supporting higher-quality speech generation with larger codebooks.

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the complex speech signal into a finite and compact latent space, named scalar latent space. Benefits from SQ-Codec, we apply a novel transformer diffusion model in the scalar latent space of SQ-Codec. We train SimpleSpeech on 4k hours of a speech-only dataset, it shows natural prosody and voice cloning ability. Compared with previous large-scale TTS models, it presents significant speech quality and generation speed improvement. Demos are released., Comment: Accepted by InterSpeech 2024

Audio-visual target speech extraction (AV-TSE) is one of the enabling technologies in robotics and many audio-visual applications. One of the challenges of AV-TSE is how to effectively utilize audio-visual synchronization information in the process. AV-HuBERT can be a useful pre-trained model for lip-reading, which has not been adopted by AV-TSE. In this paper, we would like to explore the way to integrate a pre-trained AV-HuBERT into our AV-TSE system. We have good reasons to expect an improved performance. To benefit from the inter and intra-modality correlations, we also propose a novel Mask-And-Recover (MAR) strategy for self-supervised learning. The experimental results on the VoxCeleb2 dataset show that our proposed model outperforms the baselines both in terms of subjective and objective metrics, suggesting that the pre-trained AV-HuBERT model provides more informative visual cues for target speech extraction. Furthermore, through a comparative study, we confirm that the proposed Mask-And-Recover strategy is significantly effective., Comment: Accepted by IJCNN 2024

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation.

Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech by improving the intelligibility and naturalness. This is a challenging task especially for patients with severe dysarthria and speaking in complex, noisy acoustic environments. To address these challenges, we propose a novel multi-modal framework to utilize visual information, e.g., lip movements, in DSR as extra clues for reconstructing the highly abnormal pronunciations. The multi-modal framework consists of: (i) a multi-modal encoder to extract robust phoneme embeddings from dysarthric speech with auxiliary visual features; (ii) a variance adaptor to infer the normal phoneme duration and pitch contour from the extracted phoneme embeddings; (iii) a speaker encoder to encode the speaker's voice characteristics; and (iv) a mel-decoder to generate the reconstructed mel-spectrogram based on the extracted phoneme embeddings, prosodic features and speaker embeddings. Both objective and subjective evaluations conducted on the commonly used UASpeech corpus show that our proposed approach can achieve significant improvements over baseline systems in terms of speech intelligibility and naturalness, especially for the speakers with more severe symptoms. Compared with original dysarthric speech, the reconstructed speech achieves 42.1\% absolute word error rate reduction for patients with more severe dysarthria levels., Comment: Accepted by ICASSP 2024

Dysarthric speech reconstruction (DSR) systems aim to automatically convert dysarthric speech into normal-sounding speech. The technology eases communication with speakers affected by the neuromotor disorder and enhances their social inclusion. NED-based (Neural Encoder-Decoder) systems have significantly improved the intelligibility of the reconstructed speech as compared with GAN-based (Generative Adversarial Network) approaches, but the approach is still limited by training inefficiency caused by the cascaded pipeline and auxiliary tasks of the content encoder, which may in turn affect the quality of reconstruction. Inspired by self-supervised speech representation learning and discrete speech units, we propose a Unit-DSR system, which harnesses the powerful domain-adaptation capacity of HuBERT for training efficiency improvement and utilizes speech units to constrain the dysarthric content restoration in a discrete linguistic space. Compared with NED approaches, the Unit-DSR system only consists of a speech unit normalizer and a Unit HiFi-GAN vocoder, which is considerably simpler without cascaded sub-modules or auxiliary tasks. Results on the UASpeech corpus indicate that Unit-DSR outperforms competitive baselines in terms of content restoration, reaching a 28.2% relative average word error rate reduction when compared to original dysarthric speech, and shows robustness against speed perturbation and noise., Comment: Accepted to ICASSP 2024

End-to-end multi-talker speech recognition has garnered great interest as an effective approach to directly transcribe overlapped speech from multiple speakers. Current methods typically adopt either 1) single-input multiple-output (SIMO) models with a branched encoder, or 2) single-input single-output (SISO) models based on attention-based encoder-decoder architecture with serialized output training (SOT). In this work, we propose a Cross-Speaker Encoding (CSE) network to address the limitations of SIMO models by aggregating cross-speaker representations. Furthermore, the CSE model is integrated with SOT to leverage both the advantages of SIMO and SISO while mitigating their drawbacks. To the best of our knowledge, this work represents an early effort to integrate SIMO and SISO for multi-talker speech recognition. Experiments on the two-speaker LibrispeechMix dataset show that the CES model reduces word error rate (WER) by 8% over the SIMO baseline. The CSE-SOT model reduces WER by 10% overall and by 16% on high-overlap speech compared to the SOT model. Code is available at https://github.com/kjw11/CSEnet-ASR., Comment: Accepted by ICASSP2024

The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution in the training data. To address these issues, in this paper, we propose a self-supervised style enhancing method with VQ-VAE-based pre-training for expressive audiobook speech synthesis. Firstly, a text style encoder is pre-trained with a large amount of unlabeled text-only data. Secondly, a spectrogram style extractor based on VQ-VAE is pre-trained in a self-supervised manner, with plenty of audio data that covers complex style variations. Then a novel architecture with two encoder-decoder paths is specially designed to model the pronunciation and high-level style expressiveness respectively, with the guidance of the style extractor. Both objective and subjective evaluations demonstrate that our proposed method can effectively improve the naturalness and expressiveness of the synthesized speech in audiobook synthesis especially for the role and out-of-domain scenarios., Comment: Accepted to ICASSP 2024

Large Language models (LLM) have demonstrated the capability to handle a variety of generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific approaches, leverages LLM techniques to generate multiple types of audio (including speech, sounds, music, and singing) with given input conditions. UniAudio 1) first tokenizes all types of target audio along with other condition modalities, 2) concatenates source-target pair as a single sequence, and 3) performs next-token prediction using LLM. Also, a multi-scale Transformer model is proposed to handle the overly long sequences caused by the residual vector quantization based neural codec in tokenization. Training of UniAudio is scaled up to 165K hours of audio and 1B parameters, based on all generative tasks, aiming to obtain sufficient prior knowledge not only in the intrinsic properties of audio but also the inter-relationship between audio and other modalities. Therefore, the trained UniAudio model has the potential to become a foundation model for universal audio generation: it shows strong capability in all trained tasks and can seamlessly support new audio generation tasks after simple fine-tuning. Experiments demonstrate that UniAudio achieves state-of-the-art or at least competitive results on most of the 11 tasks. Demo and code are released at https://github.com/yangdongchao/UniAudio

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language model-based TTS models show zero-shot speaker adaptation capabilities with only a 3-second acoustic prompt of an unseen speaker. However, they are limited by the length of the acoustic prompt, which makes it difficult to clone personal speaking style. In this paper, we propose a novel zero-shot TTS model with the multi-scale acoustic prompts based on a neural codec language model VALL-E. A speaker-aware text encoder is proposed to learn the personal speaking style at the phoneme-level from the style prompt consisting of multiple sentences. Following that, a VALL-E based acoustic decoder is utilized to model the timbre from the timbre prompt at the frame-level and generate speech. The experimental results show that our proposed method outperforms baselines in terms of naturalness and speaker similarity, and can achieve better performance by scaling out to a longer style prompt., Comment: Accepted bt ICASSP 2024

This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech audio. This framework comprises two VQ-S3R learners: first, the principal learner aims to provide a generative Multi-Stage Multi-Codebook (MSMC) VQ-S3R via the MSMC-VQ-GAN combined with the contrastive S3RL, while decoding it back to the high-quality audio; then, the associate learner further abstracts the MSMC representation into a highly-compact VQ representation through a VQ-VAE. These two generative VQ-S3R learners provide profitable speech representations and pre-trained models for TTS, significantly improving synthesis quality with the lower requirement for supervised data. QS-TTS is evaluated comprehensively under various scenarios via subjective and objective tests in experiments. The results powerfully demonstrate the superior performance of QS-TTS, winning the highest MOS over supervised or semi-supervised baseline TTS approaches, especially in low-resource scenarios. Moreover, comparing various speech representations and transfer learning methods in TTS further validates the notable improvement of the proposed VQ-S3RL to TTS, showing the best audio quality and intelligibility metrics. The trend of slower decay in the synthesis quality of QS-TTS with decreasing supervised data further highlights its lower requirements for supervised data, indicating its great potential in low-resource scenarios.

For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the target utterance, previous works on PSP mainly focus on utilizing intrautterance linguistic information of the current utterance only. This work proposes to use inter-utterance linguistic information to improve the performance of PSP. Multi-level contextual information, which includes both inter-utterance and intrautterance linguistic information, is extracted by a hierarchical encoder from character level, utterance level and discourse level of the input text. Then a multi-task learning (MTL) decoder predicts prosodic boundaries from multi-level contextual information. Objective evaluation results on two datasets show that our method achieves better F1 scores in predicting prosodic word (PW), prosodic phrase (PPH) and intonational phrase (IPH). It demonstrates the effectiveness of using multi-level contextual information for PSP. Subjective preference tests also indicate the naturalness of synthesized speeches are improved., Comment: Accepted by Interspeech2022

Expressive speech synthesis is crucial for many human-computer interaction scenarios, such as audiobooks, podcasts, and voice assistants. Previous works focus on predicting the style embeddings at one single scale from the information within the current sentence. Whereas, context information in neighboring sentences and multi-scale nature of style in human speech are neglected, making it challenging to convert multi-sentence text into natural and expressive speech. In this paper, we propose MSStyleTTS, a style modeling method for expressive speech synthesis, to capture and predict styles at different levels from a wider range of context rather than a sentence. Two sub-modules, including multi-scale style extractor and multi-scale style predictor, are trained together with a FastSpeech 2 based acoustic model. The predictor is designed to explore the hierarchical context information by considering structural relationships in context and predict style embeddings at global-level, sentence-level and subword-level. The extractor extracts multi-scale style embedding from the ground-truth speech and explicitly guides the style prediction. Evaluations on both in-domain and out-of-domain audiobook datasets demonstrate that the proposed method significantly outperforms the three baselines. In addition, we conduct the analysis of the context information and multi-scale style representations that have never been discussed before., Comment: Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing

Multi-talker overlapped speech poses a significant challenge for speech recognition and diarization. Recent research indicated that these two tasks are inter-dependent and complementary, motivating us to explore a unified modeling method to address them in the context of overlapped speech. A recent study proposed a cost-effective method to convert a single-talker automatic speech recognition (ASR) system into a multi-talker one, by inserting a Sidecar separator into the frozen well-trained ASR model. Extending on this, we incorporate a diarization branch into the Sidecar, allowing for unified modeling of both ASR and diarization with a negligible overhead of only 768 parameters. The proposed method yields better ASR results compared to the baseline on LibriMix and LibriSpeechMix datasets. Moreover, without sophisticated customization on the diarization task, our method achieves acceptable diarization results on the two-speaker subset of CALLHOME with only a few adaptation steps., Comment: Accepted to INTERSPEECH 2023

As a common way of emotion signaling via non-linguistic vocalizations, vocal burst (VB) plays an important role in daily social interaction. Understanding and modeling human vocal bursts are indispensable for developing robust and general artificial intelligence. Exploring computational approaches for understanding vocal bursts is attracting increasing research attention. In this work, we propose a hierarchical framework, based on chain regression models, for affective recognition from VBs, that explicitly considers multiple relationships: (i) between emotional states and diverse cultures; (ii) between low-dimensional (arousal & valence) and high-dimensional (10 emotion classes) emotion spaces; and (iii) between various emotion classes within the high-dimensional space. To address the challenge of data sparsity, we also use self-supervised learning (SSL) representations with layer-wise and temporal aggregation modules. The proposed systems participated in the ACII Affective Vocal Burst (A-VB) Challenge 2022 and ranked first in the "TWO'' and "CULTURE'' tasks. Experimental results based on the ACII Challenge 2022 dataset demonstrate the superior performance of the proposed system and the effectiveness of considering multiple relationships using hierarchical regression chain models., Comment: 5 pages, 3 figures, 5 tables

With the global population aging rapidly, Alzheimer's disease (AD) is particularly prominent in older adults, which has an insidious onset and leads to a gradual, irreversible deterioration in cognitive domains (memory, communication, etc.). Speech-based AD detection opens up the possibility of widespread screening and timely disease intervention. Recent advances in pre-trained models motivate AD detection modeling to shift from low-level features to high-level representations. This paper presents several efficient methods to extract better AD-related cues from high-level acoustic and linguistic features. Based on these features, the paper also proposes a novel task-oriented approach by modeling the relationship between the participants' description and the cognitive task. Experiments are carried out on the ADReSS dataset in a binary classification setup, and models are evaluated on the unseen test set. Results and comparison with recent literature demonstrate the efficiency and superior performance of proposed acoustic, linguistic and task-oriented methods. The findings also show the importance of semantic and syntactic information, and feasibility of automation and generalization with the promising audio-only and task-oriented methods for the AD detection task., Comment: 5 pages, 3 figures, 3 tables

Although automatic speech recognition (ASR) can perform well in common non-overlapping environments, sustaining performance in multi-talker overlapping speech recognition remains challenging. Recent research revealed that ASR model's encoder captures different levels of information with different layers -- the lower layers tend to have more acoustic information, and the upper layers more linguistic. This inspires us to develop a Sidecar separator to empower a well-trained ASR model for multi-talker scenarios by separating the mixed speech embedding between two suitable layers. We experimented with a wav2vec 2.0-based ASR model with a Sidecar mounted. By freezing the parameters of the original model and training only the Sidecar (8.7 M, 8.4% of all parameters), the proposed approach outperforms the previous state-of-the-art by a large margin for the 2-speaker mixed LibriMix dataset, reaching a word error rate (WER) of 10.36%; and obtains comparable results (7.56%) for LibriSpeechMix dataset when limited training., Comment: Accepted by IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

Homophone characters are common in tonal syllable-based languages, such as Mandarin and Cantonese. The data-intensive end-to-end Automatic Speech Recognition (ASR) systems are more likely to mis-recognize homophone characters and rare words under low-resource settings. For the problem of lowresource Cantonese speech recognition, this paper presents a novel homophone extension method to integrate human knowledge of the homophone lexicon into the beam search decoding process with language model re-scoring. Besides, we propose an automatic unified writing method to merge the variants of Cantonese characters and standardize speech annotation guidelines, which enables more efficient utilization of labeled utterances by providing more samples for the merged characters. We empirically show that both homophone extension and unified writing improve the recognition performance significantly on both in-domain and out-of-domain test sets, with an absolute Character Error Rate (CER) decrease of around 5% and 18%., Comment: The 13th International Symposium on Chinese Spoken Language Processing (ISCSLP 2022)

This paper aims to enhance low-resource TTS by reducing training data requirements using compact speech representations. A Multi-Stage Multi-Codebook (MSMC) VQ-GAN is trained to learn the representation, MSMCR, and decode it to waveforms. Subsequently, we train the multi-stage predictor to predict MSMCRs from the text for TTS synthesis. Moreover, we optimize the training strategy by leveraging more audio to learn MSMCRs better for low-resource languages. It selects audio from other languages using speaker similarity metric to augment the training set, and applies transfer learning to improve training quality. In MOS tests, the proposed system significantly outperforms FastSpeech and VITS in standard and low-resource scenarios, showing lower data requirements. The proposed training strategy effectively enhances MSMCRs on waveform reconstruction. It improves TTS performance further, which wins 77% votes in the preference test for the low-resource TTS with only 15 minutes of paired data., Comment: Submitted to ICASSP 2023

We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the effectiveness of the disentanglement. Inspired by $\beta$-VAE, we introduce a learning objective that balances between the information captured by the content and speaker representations. In addition, the inductive biases from the architectural design and the training dataset further encourage the desired disentanglement. Both objective and subjective evaluations show the effectiveness of the proposed method in speech disentanglement and in one-shot cross-lingual voice conversion., Comment: Accepted at SLT 2022

We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data by down-sampling progressively in multiple stages into MSMC Representations (MSMCRs) with different time resolutions, and quantizing them with multiple VQ codebooks, respectively. Multi-stage predictors are trained to map the input text sequence to MSMCRs progressively by minimizing a combined loss of the reconstruction Mean Square Error (MSE) and "triplet loss". In synthesis, the neural vocoder converts the predicted MSMCRs into final speech waveforms. The proposed approach is trained and tested with an English TTS database of 16 hours by a female speaker. The proposed TTS achieves an MOS score of 4.41, which outperforms the baseline with an MOS of 3.62. Compact versions of the proposed TTS with much less parameters can still preserve high MOS scores. Ablation studies show that both multiple stages and multiple codebooks are effective for achieving high TTS performance.

Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and delay progression. Speech based automatic AD screening systems provide a non-intrusive and more scalable alternative to other clinical screening techniques. Scarcity of such specialist data leads to uncertainty in both model selection and feature learning when developing such systems. To this end, this paper investigates the use of feature and model combination approaches to improve the robustness of domain fine-tuning of BERT and Roberta pre-trained text encoders on limited data, before the resulting embedding features being fed into an ensemble of backend classifiers to produce the final AD detection decision via majority voting. Experiments conducted on the ADReSS20 Challenge dataset suggest consistent performance improvements were obtained using model and feature combination in system development. State-of-the-art AD detection accuracies of 91.67 percent and 93.75 percent were obtained using manual and ASR speech transcripts respectively on the ADReSS20 test set consisting of 48 elderly speakers., Comment: Accepted by INTERSPEECH 2022

Recent years have witnessed the extraordinary development of automatic speaker verification (ASV). However, previous works show that state-of-the-art ASV models are seriously vulnerable to voice spoofing attacks, and the recently proposed high-performance spoofing countermeasure (CM) models only focus solely on the standalone anti-spoofing tasks, and ignore the subsequent speaker verification process. How to integrate the CM and ASV together remains an open question. A spoofing aware speaker verification (SASV) challenge has recently taken place with the argument that better performance can be delivered when both CM and ASV subsystems are optimized jointly. Under the challenge's scenario, the integrated systems proposed by the participants are required to reject both impostor speakers and spoofing attacks from target speakers, which intuitively and effectively matches the expectation of a reliable, spoofing-robust ASV system. This work focuses on fusion-based SASV solutions and proposes a multi-model fusion framework to leverage the power of multiple state-of-the-art ASV and CM models. The proposed framework vastly improves the SASV-EER from 8.75% to 1.17\%, which is 86% relative improvement compared to the best baseline system in the SASV challenge., Comment: Accepted by Odyssey 2022

Deep neural networks have brought significant advancements to speech emotion recognition (SER). However, the architecture design in SER is mainly based on expert knowledge and empirical (trial-and-error) evaluations, which is time-consuming and resource intensive. In this paper, we propose to apply neural architecture search (NAS) techniques to automatically configure the SER models. To accelerate the candidate architecture optimization, we propose a uniform path dropout strategy to encourage all candidate architecture operations to be equally optimized. Experimental results of two different neural structures on IEMOCAP show that NAS can improve SER performance (54.89\% to 56.28\%) while maintaining model parameter sizes. The proposed dropout strategy also shows superiority over the previous approaches., Comment: Accepted by ICASSP 2022

Recently, many novel techniques have been introduced to deal with spoofing attacks, and achieve promising countermeasure (CM) performances. However, these works only take the stand-alone CM models into account. Nowadays, a spoofing aware speaker verification (SASV) challenge which aims to facilitate the research of integrated CM and ASV models, arguing that jointly optimizing CM and ASV models will lead to better performance, is taking place. In this paper, we propose a novel multi-model and multi-level fusion strategy to tackle the SASV task. Compared with purely scoring fusion and embedding fusion methods, this framework first utilizes embeddings from CM models, propagating CM embeddings into a CM block to obtain a CM score. In the second-level fusion, the CM score and ASV scores directly from ASV systems will be concatenated into a prediction block for the final decision. As a result, the best single fusion system has achieved the SASV-EER of 0.97% on the evaluation set. Then by ensembling the top-5 fusion systems, the final SASV-EER reached 0.89%., Comment: Submitted to Interspeech 2022

The generative adversarial network (GAN) has shown its outstanding capability in improving Non-Autoregressive TTS (NAR-TTS) by adversarially training it with an extra model that discriminates between the real and the generated speech. To maximize the benefits of GAN, it is crucial to find a powerful discriminator that can capture rich distinguishable information. In this paper, we propose a multi-scale time-frequency spectrogram discriminator to help NAR-TTS generate high-fidelity Mel-spectrograms. It treats the spectrogram as a 2D image to exploit the correlation among different components in the time-frequency domain. And a U-Net-based model structure is employed to discriminate at different scales to capture both coarse-grained and fine-grained information. We conduct subjective tests to evaluate the proposed approach. Both multi-scale and time-frequency discriminating bring significant improvement in the naturalness and fidelity. When combining the neural vocoder, it is shown more effective and concise than fine-tuning the vocoder. Finally, we visualize the discriminating maps to compare their difference to verify the effectiveness of multi-scale discriminating., Comment: Submitted to INTERSPEECH 2022

Dysarthric speech reconstruction (DSR), which aims to improve the quality of dysarthric speech, remains a challenge, not only because we need to restore the speech to be normal, but also must preserve the speaker's identity. The speaker representation extracted by the speaker encoder (SE) optimized for speaker verification has been explored to control the speaker identity. However, the SE may not be able to fully capture the characteristics of dysarthric speakers that are previously unseen. To address this research problem, we propose a novel multi-task learning strategy, i.e., adversarial speaker adaptation (ASA). The primary task of ASA fine-tunes the SE with the speech of the target dysarthric speaker to effectively capture identity-related information, and the secondary task applies adversarial training to avoid the incorporation of abnormal speaking patterns into the reconstructed speech, by regularizing the distribution of reconstructed speech to be close to that of reference speech with high quality. Experiments show that the proposed approach can achieve enhanced speaker similarity and comparable speech naturalness with a strong baseline approach. Compared with dysarthric speech, the reconstructed speech achieves 22.3% and 31.5% absolute word error rate reduction for speakers with moderate and moderate-severe dysarthria respectively. Our demo page is released here: https://wendison.github.io/ASA-DSR-demo/, Comment: Accepted to ICASSP 2022. Demo page is available at https://wendison.github.io/ASA-DSR-demo/

This paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech recognition (ASR) tasks. In these meeting scenarios, the uncertainty of the speaker number and the high ratio of overlapped speech present great challenges for diarization. Based on the assumption that there is valuable complementary information between acoustic features, spatial-related and speaker-related features, we propose a multi-level feature fusion mechanism based target-speaker voice activity detection (FFM-TS-VAD) system to improve the performance of the conventional TS-VAD system. Furthermore, we propose a data augmentation method during training to improve the system robustness when the angular difference between two speakers is relatively small. We provide comparisons for different sub-systems we used in M2MeT challenge. Our submission is a fusion of several sub-systems and ranks second in the diarization task., Comment: submitted to ICASSP2022

A leaderboard named Speech processing Universal PERformance Benchmark (SUPERB), which aims at benchmarking the performance of a shared self-supervised learning (SSL) speech model across various downstream speech tasks with minimal modification of architectures and small amount of data, has fueled the research for speech representation learning. The SUPERB demonstrates speech SSL upstream models improve the performance of various downstream tasks through just minimal adaptation. As the paradigm of the self-supervised learning upstream model followed by downstream tasks arouses more attention in the speech community, characterizing the adversarial robustness of such paradigm is of high priority. In this paper, we make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limited-knowledge adversaries, and the attacks generated by zero-knowledge adversaries are with transferability. The XAB test verifies the imperceptibility of crafted adversarial attacks., Comment: Accepted by ICASSP 2022

Existing approaches for anti-spoofing in automatic speaker verification (ASV) still lack generalizability to unseen attacks. The Res2Net approach designs a residual-like connection between feature groups within one block, which increases the possible receptive fields and improves the system's detection generalizability. However, such a residual-like connection is performed by a direct addition between feature groups without channel-wise priority. We argue that the information across channels may not contribute to spoofing cues equally, and the less relevant channels are expected to be suppressed before adding onto the next feature group, so that the system can generalize better to unseen attacks. This argument motivates the current work that presents a novel, channel-wise gated Res2Net (CG-Res2Net), which modifies Res2Net to enable a channel-wise gating mechanism in the connection between feature groups. This gating mechanism dynamically selects channel-wise features based on the input, to suppress the less relevant channels and enhance the detection generalizability. Three gating mechanisms with different structures are proposed and integrated into Res2Net. Experimental results conducted on ASVspoof 2019 logical access (LA) demonstrate that the proposed CG-Res2Net significantly outperforms Res2Net on both the overall LA evaluation set and individual difficult unseen attacks, which also outperforms other state-of-the-art single systems, depicting the effectiveness of our method., Comment: Accepted to INTERSPEECH 2021

This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment or knowledge distillation, is cumbersome. Furthermore, hard alignment based on phoneme expansion can degrade the naturalness of the synthesized speech. In contrast, the proposed model of VAENAR-TTS is an end-to-end approach that does not require phoneme-level durations. The VAENAR-TTS model does not contain recurrent structures and is completely non-autoregressive in both the training and inference phases. Based on the VAE architecture, the alignment information is encoded in the latent variable, and attention-based soft alignment between the text and the latent variable is used in the decoder to reconstruct the spectrogram. Experiments show that VAENAR-TTS achieves state-of-the-art synthesis quality, while the synthesis speed is comparable with other NAR-TTS models.

Dysarthric speech recognition is a challenging task as dysarthric data is limited and its acoustics deviate significantly from normal speech. Model-based speaker adaptation is a promising method by using the limited dysarthric speech to fine-tune a base model that has been pre-trained from large amounts of normal speech to obtain speaker-dependent models. However, statistic distribution mismatches between the normal and dysarthric speech data limit the adaptation performance of the base model. To address this problem, we propose to re-initialize the base model via meta-learning to obtain a better model initialization. Specifically, we focus on end-to-end models and extend the model-agnostic meta learning (MAML) and Reptile algorithms to meta update the base model by repeatedly simulating adaptation to different dysarthric speakers. As a result, the re-initialized model acquires dysarthric speech knowledge and learns how to perform fast adaptation to unseen dysarthric speakers with improved performance. Experimental results on UASpeech dataset show that the best model with proposed methods achieves 54.2% and 7.6% relative word error rate reduction compared with the base model without finetuning and the model directly fine-tuned from the base model, respectively, and it is comparable with the state-of-the-art hybrid DNN-HMM model., Comment: To appear in ISCSLP2021