Siqi Zheng

Zhihao Du, Shiliang Zhang, Kai Hu et al.

This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an extension of the open-source speech processing toolkit FunASR. FunCodec provides reproducible training recipes and inference scripts for the latest neural speech codec models, such as SoundStream and Encodec. Thanks to the unified design with FunASR, FunCodec can be easily integrated into downstream tasks, such as speech recognition. Along with FunCodec, pre-trained models are also provided, which can be used for academic or generalized purposes. Based on the toolkit, we further propose the frequency-domain codec models, FreqCodec, which can achieve comparable speech quality with much lower computation and parameter complexity. Experimental results show that, under the same compression ratio, FunCodec can achieve better reconstruction quality compared with other toolkits and released models. We also demonstrate that the pre-trained models are suitable for downstream tasks, including automatic speech recognition and personalized text-to-speech synthesis. This toolkit is publicly available at https://github.com/alibaba-damo-academy/FunCodec.

Zhihao Du, Qian Chen, Shiliang Zhang et al.

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discretized into token sequences, which are modeled by an LLM with text as prompts and reconstructed by a token-based vocoder to waveforms. Obviously, speech tokens play a critical role in LLM-based TTS models. Current speech tokens are learned in an unsupervised manner, which lacks explicit semantic information and alignment to the text. In this paper, we propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder. Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis. Experimental results show that supervised semantic tokens significantly outperform existing unsupervised tokens in terms of content consistency and speaker similarity for zero-shot voice cloning. Moreover, we find that utilizing large-scale data further improves the synthesis performance, indicating the scalable capacity of CosyVoice. To the best of our knowledge, this is the first attempt to involve supervised speech tokens into TTS models.

Qian Chen, Wen Wang, Qinglin Zhang et al.

Recently, unified speech-text models, such as SpeechGPT, VioLA, and AudioPaLM, have achieved remarkable performance on various speech tasks. These models discretize speech signals into tokens (speech discretization) and use a shared vocabulary for both text and speech tokens. Then they train a single decoder-only Transformer on a mixture of speech tasks. However, these models rely on the Loss Masking strategy for the ASR task, which ignores the dependency among speech tokens. In this paper, we propose to model speech tokens in an autoregressive way, similar to text. We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach. To address this issue, we propose a novel approach denoted Smoothed Label Distillation (SLD), which applies a KL divergence loss with smoothed labels on speech tokens. Our experiments show that SLD effectively models speech tokens and outperforms Loss Masking for decoder-only Transformers in ASR tasks with different speech discretization methods. The source code can be found here: https://github.com/alibaba-damo-academy/SpokenNLP/tree/main/sld

Zhihao Du, Jiaming Wang, Qian Chen et al.

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for audio-and-text large language models (LLMs). Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text translation, and speech enhancement over models using continuous speech features. In this paper, we propose LauraGPT, a novel unified audio-and-text GPT-based LLM for audio recognition, understanding, and generation. LauraGPT is a versatile LLM that can process both audio and text inputs and generate outputs in either modalities. We propose a novel data representation that combines continuous and discrete features for audio: LauraGPT encodes input audio into continuous representations using an audio encoder and generates output audio from discrete codec codes. We propose a one-step codec vocoder to overcome the prediction challenge caused by the multimodal distribution of codec tokens. We fine-tune LauraGPT using supervised multi-task learning. Extensive experiments show that LauraGPT consistently achieves comparable to superior performance compared to strong baselines on a wide range of audio tasks related to content, semantics, paralinguistics, and audio-signal analysis, such as automatic speech recognition, speech-to-text translation, text-to-speech synthesis, speech enhancement, automated audio captioning, speech emotion recognition, and spoken language understanding.

Siqi Zheng, Luyao Cheng, Yafeng Chen et al.

Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community. Different speech-related tasks focus on extracting distinct speech representations while minimizing the affects of other uncorrelated information. We present a large-scale speech corpus to facilitate the research of speech representation disentanglement. 3D-Speaker contains over 10,000 speakers, each of whom are simultaneously recorded by multiple Devices, locating at different Distances, and some speakers are speaking multiple Dialects. The controlled combinations of multi-dimensional audio data yield a matrix of a diverse blend of speech representation entanglement, thereby motivating intriguing methods to untangle them. The multi-domain nature of 3D-Speaker also makes it a suitable resource to evaluate large universal speech models and experiment methods of out-of-domain learning and self-supervised learning. https://3dspeaker.github.io/

Zhihao Du, Shiliang Zhang, Siqi Zheng et al.

Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with the power set, which represents the possible combinations of target speakers. This formulation has two benefits. First, the overlaps of target speakers are explicitly modeled. Second, threshold selection is no longer needed. Through this formulation, we propose the speaker embedding-aware neural diarization (SEND) framework, where a speech encoder, a speaker encoder, two similarity scorers, and a post-processing network are jointly optimized to predict the encoded labels according to the similarities between speech features and speaker embeddings. Experimental results show that SEND has a stable learning process and can be trained on highly overlapped data without extra initialization. More importantly, our method achieves the state-of-the-art performance in real meeting scenarios with fewer model parameters and lower computational complexity.

Luyao Cheng, Siqi Zheng, Qinglin Zhang et al.

Speaker diarization has gained considerable attention within speech processing research community. Mainstream speaker diarization rely primarily on speakers' voice characteristics extracted from acoustic signals and often overlook the potential of semantic information. Considering the fact that speech signals can efficiently convey the content of a speech, it is of our interest to fully exploit these semantic cues utilizing language models. In this work we propose a novel approach to effectively leverage semantic information in clustering-based speaker diarization systems. Firstly, we introduce spoken language understanding modules to extract speaker-related semantic information and utilize these information to construct pairwise constraints. Secondly, we present a novel framework to integrate these constraints into the speaker diarization pipeline, enhancing the performance of the entire system. Extensive experiments conducted on the public dataset demonstrate the consistent superiority of our proposed approach over acoustic-only speaker diarization systems.

Luyao Cheng, Hui Wang, Siqi Zheng et al.

Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing speaker diarization systems rely exclusively on unimodal acoustic information, making the task particularly challenging due to the innate ambiguities of audio signals. Recent studies have made tremendous efforts towards audio-visual or audio-semantic modeling to enhance performance. However, even the incorporation of up to two modalities often falls short in addressing the complexities of spontaneous and unstructured conversations. To exploit more meaningful dialogue patterns, we propose a novel multimodal approach that jointly utilizes audio, visual, and semantic cues to enhance speaker diarization. Our method elegantly formulates the multimodal modeling as a constrained optimization problem. First, we build insights into the visual connections among active speakers and the semantic interactions within spoken content, thereby establishing abundant pairwise constraints. Then we introduce a joint pairwise constraint propagation algorithm to cluster speakers based on these visual and semantic constraints. This integration effectively leverages the complementary strengths of different modalities, refining the affinity estimation between individual speaker embeddings. Extensive experiments conducted on multiple multimodal datasets demonstrate that our approach consistently outperforms state-of-the-art speaker diarization methods.

Weiye Xu, Zhang Jiang, Siqi Zheng et al.

With the rapid advancement of smart glasses, voice interaction has been widely adopted due to its naturalness and convenience. However, its practical deployment is often undermined by vulnerability to spoofing attacks, while no public dataset currently exists for voice liveness detection and authentication in smart-glasses scenarios. To address this challenge, we first collect a multi-acoustic-modal dataset comprising 16-channel audio data from 42 subjects, along with corresponding attack samples covering two attack categories. Based on insights derived from this collected data, we propose AuthG-Live, a sound-field-based voice liveness detection method, and AuthG-Net, a multi-acoustic-modal authentication model. We further benchmark seven voice liveness detection methods and four authentication methods across diverse acoustic modalities. The results demonstrate that our proposed approach achieves state-of-the-art performance on four benchmark tasks, and extensive ablation studies validate the generalizability of our methods \red{under real-world constraints}. Finally, we release this dataset, termed AuthGlass, to facilitate future research on voice liveness detection and authentication for smart glasses.

Siqi Zheng, Hongbin Suo

Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and agglomerative hierarchical clustering only take into account properties such as proximity and relative densities. In this paper we propose to view clustering-based diarization as a community detection problem. By doing so the topological structure is considered. This work has four major contributions. First it is shown that Leiden community detection algorithm significantly outperforms the previous methods on the clustering of speaker-segments. Second, we propose to use uniform manifold approximation to reduce dimension while retaining global and local topological structure. Third, a masked filtering approach is introduced to extract "clean" speaker embeddings. Finally, the community structure is applied to an end-to-end post-processing network to obtain diarization results. The final system presents a relative DER reduction of up to 70 percent. The breakdown contribution of each component is analyzed.

Jianhong Tu, Zeyu Cui, Xiaohuan Zhou et al.

The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and emotions, which over-simplifies the problem by classifying styles and emotions into a fixed number of pre-defined categories. In this paper, we introduce a new task setting, Contextual TTS (CTTS). The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. Thus, in the CTTS task, we propose to utilize such context to guide the speech synthesis process instead of relying on explicit labels of styles and emotions. To achieve this task, we construct a synthetic dataset and develop an effective framework. Experiments show that our framework can generate high-quality expressive speech based on the given context both in synthetic datasets and real-world scenarios.

Qian Chen, Wen Wang, Qinglin Zhang et al.

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers. However, the vanilla BERT uses the same self-attention mechanism for each layer to model the different contextual features. In this paper, we propose a HybridBERT model which combines self-attention and pooling networks to encode different contextual features in each layer. Additionally, we propose a simple DropMask method to address the mismatch between pre-training and fine-tuning caused by excessive use of special mask tokens during Masked Language Modeling pre-training. Experiments show that HybridBERT outperforms BERT in pre-training with lower loss, faster training speed (8% relative), lower memory cost (13% relative), and also in transfer learning with 1.5% relative higher accuracies on downstream tasks. Additionally, DropMask improves accuracies of BERT on downstream tasks across various masking rates.

Shengpeng Ji, Qian Chen, Wen Wang et al.

In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice without further control and adjustment capabilities while prior controllable TTS models cannot perform speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging task: a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and utilizes bidirectional attention and mask-based parallel decoding to capture codec representations corresponding to timbre, content, and style in a discrete decoupling codec space. Moreover, we analyze the many-to-many issue in textual style control and propose the Style Mixture Semantic Density (SMSD) module, which is based on Gaussian mixture density networks, to resolve this problem. To facilitate empirical validations, we make available a new style controllable dataset called VccmDataset. Our experimental results demonstrate that ControlSpeech exhibits comparable or state-of-the-art (SOTA) performance in terms of controllability, timbre similarity, audio quality, robustness, and generalizability. The relevant code and demo are available at https://github.com/jishengpeng/ControlSpeech .

Ziyang Ma, Guanrou Yang, Yifan Yang et al.

In this paper, we focus on solving one of the most important tasks in the field of speech processing, i.e., automatic speech recognition (ASR), with speech foundation encoders and large language models (LLM). Recent works have complex designs such as compressing the output temporally for the speech encoder, tackling modal alignment for the projector, and utilizing parameter-efficient fine-tuning for the LLM. We found that delicate designs are not necessary, while an embarrassingly simple composition of off-the-shelf speech encoder, LLM, and the only trainable linear projector is competent for the ASR task. To be more specific, we benchmark and explore various combinations of LLMs and speech encoders, leading to the optimal LLM-based ASR system, which we call SLAM-ASR. The proposed SLAM-ASR provides a clean setup and little task-specific design, where only the linear projector is trained. To the best of our knowledge, SLAM-ASR achieves the best performance on the Librispeech benchmark among LLM-based ASR models and even outperforms the latest LLM-based audio-universal model trained on massive pair data. Finally, we explore the capability emergence of LLM-based ASR in the process of modal alignment. We hope that our study can facilitate the research on extending LLM with cross-modality capacity and shed light on the LLM-based ASR community.

Qinglin Zhang, Luyao Cheng, Chong Deng et al.

Full-duplex spoken dialogue systems significantly surpass traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and natural interactions in full-duplex dialogue systems remains a significant challenge, especially considering human conversation dynamics such as interruptions, backchannels, and overlapping speech. In this paper, we introduce a novel End-to-End GPT-based model OmniFlatten for full-duplex conversation, capable of effectively modeling the complex behaviors inherent to natural conversations with low latency. To achieve full-duplex conversation capabilities, we propose a multi-stage post-training scheme that progressively adapts a text large language model (LLM) backbone into a speech-text dialogue LLM, capable of generating text and speech in real time, without modifying the architecture of the backbone LLM. The training process comprises three stages: modality alignment, half-duplex dialogue learning, and full-duplex dialogue learning. In all training stages, we standardize the data using a flattening operation, which enables unifying the training methods and the GPT backbone across different modalities and tasks. Our approach offers a simple modeling technique and a promising research direction for developing efficient and natural end-to-end full-duplex spoken dialogue systems. Audio samples of dialogues generated by OmniFlatten can be found at this web site (https://omniflatten.github.io/).

Ruiqi Li, Siqi Zheng, Xize Cheng et al.

Generating music that aligns with the visual content of a video has been a challenging task, as it requires a deep understanding of visual semantics and involves generating music whose melody, rhythm, and dynamics harmonize with the visual narratives. This paper presents MuVi, a novel framework that effectively addresses these challenges to enhance the cohesion and immersive experience of audio-visual content. MuVi analyzes video content through a specially designed visual adaptor to extract contextually and temporally relevant features. These features are used to generate music that not only matches the video's mood and theme but also its rhythm and pacing. We also introduce a contrastive music-visual pre-training scheme to ensure synchronization, based on the periodicity nature of music phrases. In addition, we demonstrate that our flow-matching-based music generator has in-context learning ability, allowing us to control the style and genre of the generated music. Experimental results show that MuVi demonstrates superior performance in both audio quality and temporal synchronization. The generated music video samples are available at https://muvi-v2m.github.io.

Xize Cheng, Siqi Zheng, Zehan Wang et al.

The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtracks based on omni-modal queries, encompassing both single-modal and multi-modal composed queries. Specifically, we introduce the Query-Mixup strategy, which blends query features from different modalities during training. This enables OmniSep to optimize multiple modalities concurrently, effectively bringing all modalities under a unified framework for sound separation. We further enhance this flexibility by allowing queries to influence sound separation positively or negatively, facilitating the retention or removal of specific sounds as desired. Finally, OmniSep employs a retrieval-augmented approach known as Query-Aug, which enables open-vocabulary sound separation. Experimental evaluations on MUSIC, VGGSOUND-CLEAN+, and MUSIC-CLEAN+ datasets demonstrate effectiveness of OmniSep, achieving state-of-the-art performance in text-, image-, and audio-queried sound separation tasks. For samples and further information, please visit the demo page at \url{https://omnisep.github.io/}.

Qian Chen, Wen Wang, Qinglin Zhang et al.

Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e.g., BERT, without fine-tuning. Our analysis reveals that the sentence embeddings from BERT suffer from a bias towards uninformative words, limiting the performance in semantic textual similarity (STS) tasks. To address this bias, we propose a simple and efficient unsupervised approach, Diagonal Attention Pooling (Ditto), which weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings. Ditto can be easily applied to any pre-trained language model as a postprocessing operation. Compared to prior sentence embedding approaches, Ditto does not add parameters nor requires any learning. Empirical evaluations demonstrate that our proposed Ditto can alleviate the anisotropy problem and improve various pre-trained models on STS tasks.

Fan Yu, Shiliang Zhang, Pengcheng Guo et al.

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.

Fan Yu, Shiliang Zhang, Yihui Fu et al.

Recent development of speech processing, such as speech recognition, speaker diarization, etc., has inspired numerous applications of speech technologies. The meeting scenario is one of the most valuable and, at the same time, most challenging scenarios for the deployment of speech technologies. Specifically, two typical tasks, speaker diarization and multi-speaker automatic speech recognition have attracted much attention recently. However, the lack of large public meeting data has been a major obstacle for the advancement of the field. Therefore, we make available the AliMeeting corpus, which consists of 120 hours of recorded Mandarin meeting data, including far-field data collected by 8-channel microphone array as well as near-field data collected by headset microphone. Each meeting session is composed of 2-4 speakers with different speaker overlap ratio, recorded in rooms with different size. Along with the dataset, we launch the ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) with two tracks, namely speaker diarization and multi-speaker ASR, aiming to provide a common testbed for meeting rich transcription and promote reproducible research in this field. In this paper we provide a detailed introduction of the AliMeeting dateset, challenge rules, evaluation methods and baseline systems.

Yuchen Chai, Juan Palacios, Jianghao Wang et al.

COVID-19, as a global health crisis, has triggered the fear emotion with unprecedented intensity. Besides the fear of getting infected, the outbreak of COVID-19 also created significant disruptions in people's daily life and thus evoked intensive psychological responses indirect to COVID-19 infections. Here, we construct an expressed fear database using 16 million social media posts generated by 536 thousand users between January 1st, 2019 and August 31st, 2020 in China. We employ deep learning techniques to detect the fear emotion within each post and apply topic models to extract the central fear topics. Based on this database, we find that sleep disorders ("nightmare" and "insomnia") take up the largest share of fear-labeled posts in the pre-pandemic period (January 2019-December 2019), and significantly increase during the COVID-19. We identify health and work-related concerns are the two major sources of fear induced by the COVID-19. We also detect gender differences, with females generating more posts containing the daily-life fear sources during the COVID-19 period. This research adopts a data-driven approach to trace back public emotion, which can be used to complement traditional surveys to achieve real-time emotion monitoring to discern societal concerns and support policy decision-making.