Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation

• URL: http://arxiv.org/abs/2505.15333v1
• Date: Wed, 21 May 2025 10:05:25 GMT
• Title: Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
• Authors: Yuhao Zhang, Xiangnan Ma, Kaiqi Kou, Peizhuo Liu, Weiqiao Shan, Benyou Wang, Tong Xiao, Yuxin Huang, Zhengtao Yu, Jingbo Zhu,
• Abstract summary: We propose the unit language to overcome the two modeling challenges.<n>The unit language can be considered a text-like representation format.<n>We implement multi-task learning to utilize the unit language in guiding the speech modeling process.
• Score: 48.769137497536
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM), and 2) learning alignment of difference languages in long sequences, called cross-lingual (CL). We propose the unit language to overcome the two modeling challenges. The unit language can be considered a text-like representation format, constructed using $n$-gram language modeling. We implement multi-task learning to utilize the unit language in guiding the speech modeling process. Our initial results reveal a conflict when applying source and target unit languages simultaneously. We propose task prompt modeling to mitigate this conflict. We conduct experiments on four languages of the Voxpupil dataset. Our method demonstrates significant improvements over a strong baseline and achieves performance comparable to models trained with text.

Related papers

• Generalized Multilingual Text-to-Speech Generation with Language-Aware Style Adaptation [18.89091877062589]
  LanStyleTTS is a non-autoregressive, language-aware style adaptive TTS framework.<n>It supports a unified multilingual TTS model capable of producing accurate and high-quality speech without the need to train language-specific models.
  arXiv  Detail & Related papers  (2025-04-11T06:12:57Z)
• Toward Joint Language Modeling for Speech Units and Text [89.32163954508489]
  We explore joint language modeling for speech units and text. We introduce automatic metrics to evaluate how well the joint LM mixes speech and text. Our results show that by mixing speech units and text with our proposed mixing techniques, the joint LM improves over a speech-only baseline on SLU tasks.
  arXiv  Detail & Related papers  (2023-10-12T20:53:39Z)
• Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation [65.13824257448564]
  This paper proposes a textless training method for many-to-many multilingual speech-to-speech translation. By treating the speech units as pseudo-text, we can focus on the linguistic content of the speech. We demonstrate that the proposed UTUT model can be effectively utilized not only for Speech-to-Speech Translation (S2ST) but also for multilingual Text-to-Speech Synthesis (T2S) and Text-to-Speech Translation (T2ST)
  arXiv  Detail & Related papers  (2023-08-03T15:47:04Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• Textless Speech-to-Speech Translation With Limited Parallel Data [51.3588490789084]
  PFB is a framework for training textless S2ST models that require just dozens of hours of parallel speech data. We train and evaluate our models for English-to-German, German-to-English and Marathi-to-English translation on three different domains.
  arXiv  Detail & Related papers  (2023-05-24T17:59:05Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)

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.