StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

• URL: http://arxiv.org/abs/2306.07691v2
• Date: Mon, 20 Nov 2023 04:23:08 GMT
• Title: StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
• Authors: Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler, Nima Mesgarani
• Abstract summary: StyleTTS 2 is a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs.
• Score: 19.029030168939354
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.

Related papers

• Multi-modal Adversarial Training for Zero-Shot Voice Cloning [9.823246184635103]
  We propose a Transformer encoder-decoder architecture to conditionally discriminate between real and generated speech features. We introduce our novel adversarial training technique by applying it to a FastSpeech2 acoustic model and training on Libriheavy, a large multi-speaker dataset. Our model achieves improvements over the baseline in terms of speech quality and speaker similarity.
  arXiv  Detail & Related papers  (2024-08-28T16:30:41Z)
• 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)
• DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer [9.032701216955497]
  We present an efficient and scalable Diffusion Transformer (DiT) that utilizes off-the-shelf pre-trained text and speech encoders. Our approach addresses the challenge of text-speech alignment via cross-attention mechanisms with the prediction of the total length of speech representations. We scale the training dataset and the model size to 82K hours and 790M parameters, respectively.
  arXiv  Detail & Related papers  (2024-06-17T11:25:57Z)
• Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech [6.243356997302935]
  We introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations from recordings in the target language, which are then used to train a single-speaker acoustic model.
  arXiv  Detail & Related papers  (2023-09-15T09:03:14Z)
• Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer [53.72998363956454]
  Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy. The scarcity of high-quality speaker-parallel data poses a challenge for learning style transfer during translation. We design an S2ST pipeline with style-transfer capability on the basis of discrete self-supervised speech representations and timbre units.
  arXiv  Detail & Related papers  (2023-09-14T09:52:08Z)
• Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias [71.94109664001952]
  Mega-TTS is a novel zero-shot TTS system that is trained with large-scale wild data. We show that Mega-TTS surpasses state-of-the-art TTS systems on zero-shot TTS speech editing, and cross-lingual TTS tasks.
  arXiv  Detail & Related papers  (2023-06-06T08:54:49Z)
• Textually Pretrained Speech Language Models [107.10344535390956]
  We propose TWIST, a method for training SpeechLMs using a warm-start from a pretrained textual language models. We show using both automatic and human evaluations that TWIST outperforms a cold-start SpeechLM across the board.
  arXiv  Detail & Related papers  (2023-05-22T13:12:16Z)
• ArmanTTS single-speaker Persian dataset [2.7836084563851284]
  This paper introduces the single speaker dataset: ArmanTTS. We show that ArmanTTS meets the necessary standards for teaching a Persian text-to-speech conversion model. We also combined the Tacotron 2 and HiFi GAN to design a model that can receive phonemes as input, with the output being the corresponding speech.
  arXiv  Detail & Related papers  (2023-04-07T10:52:55Z)
• GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech Synthesis [68.42632589736881]
  This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice. GenerSpeech decomposes the speech variation into the style-agnostic and style-specific parts by introducing two components. Our evaluations on zero-shot style transfer demonstrate that GenerSpeech surpasses the state-of-the-art models in terms of audio quality and style similarity.
  arXiv  Detail & Related papers  (2022-05-15T08:16:02Z)
• Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis [39.730034713382736]
  Cross-speaker style transfer (CSST) in text-to-speech (TTS) aims at transferring a speaking style to the synthesised speech in a target speaker's voice. This presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text.
  arXiv  Detail & Related papers  (2021-09-08T05:39:34Z)
• Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation [63.561944239071615]
  StyleSpeech is a new TTS model which synthesizes high-quality speech and adapts to new speakers. With SALN, our model effectively synthesizes speech in the style of the target speaker even from single speech audio. We extend it to Meta-StyleSpeech by introducing two discriminators trained with style prototypes, and performing episodic training.
  arXiv  Detail & Related papers  (2021-06-06T15:34:11Z)

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.