RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis

• URL: http://arxiv.org/abs/2404.03204v3
• Date: Sun, 19 May 2024 21:34:28 GMT
• Title: RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis
• Authors: Detai Xin, Xu Tan, Kai Shen, Zeqian Ju, Dongchao Yang, Yuancheng Wang, Shinnosuke Takamichi, Hiroshi Saruwatari, Shujie Liu, Jinyu Li, Sheng Zhao,
• Abstract summary: RALL-E is a robust language modeling method for text-to-speech synthesis. RALL-E improves the WER of zero-shot TTS from $5.6%$ (without reranking) to $2.5%$ and $1.0%$, respectively.
• Score: 84.57932472551889
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts prosody features (pitch and duration) of the input text and uses them as intermediate conditions to predict speech tokens in a CoT style. Second, RALL-E utilizes the predicted duration prompt to guide the computing of self-attention weights in Transformer to enforce the model to focus on the corresponding phonemes and prosody features when predicting speech tokens. Results of comprehensive objective and subjective evaluations demonstrate that, compared to a powerful baseline method VALL-E, RALL-E significantly improves the WER of zero-shot TTS from $5.6\%$ (without reranking) and $1.7\%$ (with reranking) to $2.5\%$ and $1.0\%$, respectively. Furthermore, we demonstrate that RALL-E correctly synthesizes sentences that are hard for VALL-E and reduces the error rate from $68\%$ to $4\%$.

Related papers

• SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models [64.40250409933752]
  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. 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.
  arXiv  Detail & Related papers  (2024-08-25T17:07:39Z)
• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
  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.
  arXiv  Detail & Related papers  (2024-07-07T15:16:19Z)
• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment [101.2489492032816]
  VALL-E R is a robust and efficient zero-shot Text-to-Speech system. This research has the potential to be applied to meaningful projects, including the creation of speech for those affected by aphasia.
  arXiv  Detail & Related papers  (2024-06-12T04:09:44Z)
• VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers [119.89284877061779]
  This paper introduces VALL-E 2, the latest advancement in neural language models that marks a milestone in zero-shot text-to-speech (TTS) VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are traditionally challenging due to their complexity or repetitive phrases. The advantages of this work could contribute to valuable endeavors, such as generating speech for individuals with aphasia or people with amyotrophic lateral sclerosis.
  arXiv  Detail & Related papers  (2024-06-08T06:31:03Z)
• BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data [15.447206120523356]
  BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data. We show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.
  arXiv  Detail & Related papers  (2024-02-12T22:21:30Z)
• Controllable Emphasis with zero data for text-to-speech [57.12383531339368]
  A simple but effective method to achieve emphasized speech consists in increasing the predicted duration of the emphasised word. We show that this is significantly better than spectrogram modification techniques improving naturalness by $7.3%$ and correct testers' identification of the emphasised word in a sentence by $40%$ on a reference female en-US voice.
  arXiv  Detail & Related papers  (2023-07-13T21:06:23Z)

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.