BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights

• URL: http://arxiv.org/abs/2501.17790v1
• Date: Wed, 29 Jan 2025 17:31:26 GMT
• Title: BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
• Authors: Chan-Jan Hsu, Yi-Cheng Lin, Chia-Chun Lin, Wei-Chih Chen, Ho Lam Chung, Chen-An Li, Yi-Chang Chen, Chien-Yu Yu, Ming-Ji Lee, Chien-Cheng Chen, Ru-Heng Huang, Hung-yi Lee, Da-Shan Shiu,
• Abstract summary: BreezyVoice is a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin. Our evaluation demonstrates BreezyVoice's superior performance in both general and code-switching contexts.
• Score: 43.04083813620365
• License:
• Abstract: We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language. Building upon CosyVoice, we incorporate a $S^{3}$ tokenizer, a large language model (LLM), an optimal-transport conditional flow matching model (OT-CFM), and a grapheme to phoneme prediction model, to generate realistic speech that closely mimics human utterances. Our evaluation demonstrates BreezyVoice's superior performance in both general and code-switching contexts, highlighting its robustness and effectiveness in generating high-fidelity speech. Additionally, we address the challenges of generalizability in modeling long-tail speakers and polyphone disambiguation. Our approach significantly enhances performance and offers valuable insights into the workings of neural codec TTS systems.

Related papers

• CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models [74.80386066714229]
  We present an improved streaming speech synthesis model, CosyVoice 2. Specifically, we introduce finite-scalar quantization to improve codebook utilization of speech tokens. We develop a chunk-aware causal flow matching model to support various synthesis scenarios.
  arXiv  Detail & Related papers  (2024-12-13T12:59:39Z)
• DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech [14.323313455208183]
  We propose a novel approach to disentangle speaker and accent representations using multi-level variational autoencoders (ML-VAE) and vector quantization (VQ) Our proposed method addresses the challenge of effectively separating speaker and accent characteristics, enabling more fine-grained control over the synthesized speech.
  arXiv  Detail & Related papers  (2024-10-17T08:51:46Z)
• EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions [152.41217651729738]
  GPT-4o is an omni-modal model that enables vocal conversations with diverse emotions and tones. We propose EMOVA to enable Large Language Models with end-to-end speech capabilities. For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks.
  arXiv  Detail & Related papers  (2024-09-26T16:44:02Z)
• Cross-Dialect Text-To-Speech in Pitch-Accent Language Incorporating Multi-Dialect Phoneme-Level BERT [29.167336994990542]
  Cross-dialect text-to-speech (CD-TTS) is a task to synthesize learned speakers' voices in non-native dialects. We present a novel TTS model comprising three sub-modules to perform competitively at this task.
  arXiv  Detail & Related papers  (2024-09-11T13:40:27Z)
• FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs [63.8261207950923]
  FunAudioLLM is a model family designed to enhance natural voice interactions between humans and large language models (LLMs) At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub.
  arXiv  Detail & Related papers  (2024-07-04T16:49:02Z)
• Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer [39.31849739010572]
  We introduce textbfGenerative textbfPre-trained textbfSpeech textbfTransformer (GPST) GPST is a hierarchical transformer designed for efficient speech language modeling.
  arXiv  Detail & Related papers  (2024-06-03T04:16:30Z)
• VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation [91.39949385661379]
  VioLA is a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text. We first convert all the speech utterances to discrete tokens using an offline neural encoder. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks.
  arXiv  Detail & Related papers  (2023-05-25T14:39:47Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• Cross-lingual Low Resource Speaker Adaptation Using Phonological Features [2.8080708404213373]
  We train a language-agnostic multispeaker model conditioned on a set of phonologically derived features common across different languages. With as few as 32 and 8 utterances of target speaker data, we obtain high speaker similarity scores and naturalness comparable to the corresponding literature.
  arXiv  Detail & Related papers  (2021-11-17T12:33:42Z)
• Towards Natural and Controllable Cross-Lingual Voice Conversion Based on Neural TTS Model and Phonetic Posteriorgram [21.652906261475533]
  Cross-lingual voice conversion is a challenging problem due to significant mismatches of the phonetic set and the speech prosody of different languages. We build upon the neural text-to-speech (TTS) model to design a new cross-lingual VC framework named FastSpeech-VC.
  arXiv  Detail & Related papers  (2021-02-03T10:28:07Z)

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.