CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

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.

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

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.

LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks. However, there has been limited research on applying similar frameworks to audio tasks. Previously proposed large language models for audio tasks either lack sufficient quantitative evaluations, or are limited to tasks for recognizing and understanding audio content, or significantly underperform existing state-of-the-art (SOTA) models. In this paper, we propose LauraGPT, a unified GPT model for audio recognition, understanding, and generation. LauraGPT is a versatile language model that can process both audio and text inputs and generate outputs in either modalities. It can perform a wide range of tasks related to content, semantics, paralinguistics, and audio-signal analysis. Some of its noteworthy tasks include automatic speech recognition, speech-to-text translation, text-to-speech synthesis, machine translation, speech enhancement, automated audio captioning, speech emotion recognition, and spoken language understanding. To achieve this goal, we use a combination of continuous and discrete features for audio. We encode input audio into continuous representations using an audio encoder and decode output audio from discrete codec codes. We then fine-tune a large decoder-only Transformer-based language model on multiple audio-to-text, text-to-audio, audio-to-audio, and text-to-text tasks using a supervised multitask learning approach. Extensive experiments show that LauraGPT achieves competitive or superior performance compared to existing SOTA models on various audio processing benchmarks.

SA-Paraformer: Non-autoregressive End-to-End Speaker-Attributed ASR

Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR).Although being able to obtain state-of-the-art (SOTA) performance, most of the studies are based on an autoregressive (AR) decoder which generates tokens one-by-one and results in a large real-time factor (RTF). To speed up inference, we introduce a recently proposed non-autoregressive model Paraformer as an acoustic model in the SA-ASR model.Paraformer uses a single-step decoder to enable parallel generation, obtaining comparable performance to the SOTA AR transformer models. Besides, we propose a speaker-filling strategy to reduce speaker identification errors and adopt an inter-CTC strategy to enhance the encoder's ability in acoustic modeling. Experiments on the AliMeeting corpus show that our model outperforms the cascaded SA-ASR model by a 6.1% relative speaker-dependent character error rate (SD-CER) reduction on the test set. Moreover, our model achieves a comparable SD-CER of 34.8% with only 1/10 RTF compared with the SOTA joint AR SA-ASR model.

The second multi-channel multi-party meeting transcription challenge 2.0): A benchmark for speaker-attributed ASR

With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SA-ASR), which directly addresses the practical and challenging problem of "who spoke what at when" at typical meeting scenario. We particularly established two sub-tracks. 1) The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. 2) The open training condition sub-track, which allows for the use of all available data and models. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.

FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec

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.

CASA-ASR: Context-Aware Speaker-Attributed ASR

Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is employed to model the speaker discriminability by contrasting with speakers in the context. In addition, a two-pass decoding strategy is further proposed to fully leverage the contextual modeling ability resulting in a better recognition performance. Experimental results on AliMeeting corpus show that the proposed CASA-ASR model outperforms the original E2E SA-ASR system with a relative improvement of 11.76% in terms of speaker-dependent character error rate.

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in applications. The toolkit's flagship model, Paraformer, is a non-autoregressive end-to-end speech recognition model that has been trained on a manually annotated Mandarin speech recognition dataset that contains 60,000 hours of speech. To improve the performance of Paraformer, we have added timestamp prediction and hotword customization capabilities to the standard Paraformer backbone. In addition, to facilitate model deployment, we have open-sourced a voice activity detection model based on the Feedforward Sequential Memory Network (FSMN-VAD) and a text post-processing punctuation model based on the controllable time-delay Transformer (CT-Transformer), both of which were trained on industrial corpora. These functional modules provide a solid foundation for building high-precision long audio speech recognition services. Compared to other models trained on open datasets, Paraformer demonstrates superior performance.

TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization

Recently, end-to-end neural diarization (EEND) is introduced and achieves promising results in speaker-overlapped scenarios. In EEND, speaker diarization is formulated as a multi-label prediction problem, where speaker activities are estimated independently and their dependency are not well considered. To overcome these disadvantages, we employ the power set encoding to reformulate speaker diarization as a single-label classification problem and propose the overlap-aware EEND (EEND-OLA) model, in which speaker overlaps and dependency can be modeled explicitly. Inspired by the success of two-stage hybrid systems, we further propose a novel Two-stage OverLap-aware Diarization framework (TOLD) by involving a speaker overlap-aware post-processing (SOAP) model to iteratively refine the diarization results of EEND-OLA. Experimental results show that, compared with the original EEND, the proposed EEND-OLA achieves a 14.39% relative improvement in terms of diarization error rates (DER), and utilizing SOAP provides another 19.33% relative improvement. As a result, our method TOLD achieves a DER of 10.14% on the CALLHOME dataset, which is a new state-of-the-art result on this benchmark to the best of our knowledge.

Speaker Overlap-aware Neural Diarization for Multi-party Meeting Analysis

Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification problem, where speaker dependency and overlaps are not well considered. To overcome the disadvantages, we reformulate overlapped speaker diarization task as a single-label prediction problem via the proposed power set encoding (PSE). Through this formulation, speaker dependency and overlaps can be explicitly modeled. To fully leverage this formulation, we further propose the speaker overlap-aware neural diarization (SOND) model, which consists of a context-independent (CI) scorer to model global speaker discriminability, a context-dependent scorer (CD) to model local discriminability, and a speaker combining network (SCN) to combine and reassign speaker activities. Experimental results show that using the proposed formulation can outperform the state-of-the-art methods based on target speaker voice activity detection, and the performance can be further improved with SOND, resulting in a 6.30% relative diarization error reduction.