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

• URL: http://arxiv.org/abs/2407.05407v2
• Date: Tue, 9 Jul 2024 07:42:51 GMT
• Title: CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
• Authors: Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu, Heng Lu, Yexin Yang, Hangrui Hu, Siqi Zheng, Yue Gu, Ziyang Ma, Zhifu Gao, Zhijie Yan,
• Abstract summary: 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.
• Score: 49.569695524535454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models [45.791472119671916]
  Spoken language models (SLMs) process text and speech, enabling simultaneous speech understanding and generation. DC-Spin aims to improve speech tokenization by bridging audio signals and SLM tokens. We propose a chunk-wise approach to enable streamable DC-Spin without retraining and degradation.
  arXiv  Detail & Related papers  (2024-10-31T17:43:13Z)
• dMel: Speech Tokenization made Simple [19.169460770473908]
  We show that discretizing mel-filterbank channels into discrete intensity bins produces a simple representation (dMel) Our results demonstrate the effectiveness of dMel in achieving high performance on both tasks within a unified framework.
  arXiv  Detail & Related papers  (2024-07-22T17:51:53Z)
• Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment [19.48653924804823]
  Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the generated output can contain repeating words, missing words and mis-aligned speech. We examine these challenges in an encoder-decoder transformer model and find that certain cross-attention heads in such models implicitly learn the text and speech alignment when trained for predicting speech tokens for a given text.
  arXiv  Detail & Related papers  (2024-06-25T22:18:52Z)
• Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations [14.437646262239612]
  Self-supervised Voice Conversion (VC) architecture can be used to learn to encode transitory features, such as content, separately from stationary ones, such as speaker ID or recording conditions, creating speaker-disentangled representations. Using speaker-disentangled codes to train LLMs for text-to-speech (TTS) allows the LLM to generate the content and the style of the speech only from the text, similarly to humans, while the speaker identity is provided by the decoder of the VC model. Results show that LLMs trained over speaker-disentangled self-supervised representations provide an improvement of 4.7pp
  arXiv  Detail & Related papers  (2024-02-05T15:08:19Z)
• SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models [58.996653700982556]
  Existing speech tokens are not specifically designed for speech language modeling. We propose SpeechTokenizer, a unified speech tokenizer for speech large language models. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstrates strong performance on the SLMTokBench benchmark.
  arXiv  Detail & Related papers  (2023-08-31T12:53:09Z)
• TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition [51.565319173790314]
  TokenSplit is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.
  arXiv  Detail & Related papers  (2023-08-21T01:52:01Z)
• NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers [90.83782600932567]
  We develop NaturalSpeech 2, a TTS system that leverages a neural audio predictor with residual vectorizers to get the quantized latent vectors. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, synthesis, and voice quality in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-04-18T16:31:59Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.