Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios

• URL: http://arxiv.org/abs/2505.24691v1
• Date: Fri, 30 May 2025 15:15:00 GMT
• Title: Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios
• Authors: Gerard I. Gállego, Oriol Pareras, Martí Cortada Garcia, Lucas Takanori, Javier Hernando,
• Abstract summary: We propose a Speech-to-Text Translation (S2TT) approach that integrates phoneme representations into a Chain-of-Thought framework.<n>By introducing phoneme recognition as an intermediate step, we enhance cross-lingual transfer, enabling translation even for languages with no labeled speech data.
• Score: 10.920534445874322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a Speech-to-Text Translation (S2TT) approach that integrates phoneme representations into a Chain-of-Thought (CoT) framework to improve translation in low-resource and zero-resource settings. By introducing phoneme recognition as an intermediate step, we enhance cross-lingual transfer, enabling translation even for languages with no labeled speech data. Our system builds on a multilingual LLM, which we extend to process speech and phonemes. Training follows a curriculum learning strategy that progressively introduces more complex tasks. Experiments on multilingual S2TT benchmarks show that phoneme-augmented CoT improves translation quality in low-resource conditions and enables zero-resource translation, while slightly impacting high-resource performance. Despite this trade-off, our findings demonstrate that phoneme-based CoT is a promising step toward making S2TT more accessible across diverse languages.

Related papers

• Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation [9.118302330129284]
  This research optimize two-pass cross-lingual transfer learning in low-resource languages. We optimize phoneme vocabulary coverage by merging phonemes based on shared articulatory characteristics. We introduce a global phoneme noise generator for realistic ASR noise during phoneme-to-grapheme training to reduce error propagation.
  arXiv  Detail & Related papers  (2023-12-06T06:37:24Z)
• Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition [46.41096278421193]
  BiL-CTC+ bridges the gap between audio and text as well as between source and target languages. Our method also yields significant improvements in speech recognition performance.
  arXiv  Detail & Related papers  (2023-09-21T16:28:42Z)
• Improved Cross-Lingual Transfer Learning For Automatic Speech Translation [18.97234151624098]
  We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, we achieve significantly better cross-lingual task knowledge transfer. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl.
  arXiv  Detail & Related papers  (2023-06-01T15:19:06Z)
• ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation [79.66359274050885]
  We present ComSL, a speech-language model built atop a composite architecture of public pretrained speech-only and language-only models. Our approach has demonstrated effectiveness in end-to-end speech-to-text translation tasks.
  arXiv  Detail & Related papers  (2023-05-24T07:42:15Z)
• The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation [13.352795145385645]
  Speech translation (ST) is a good means of pretraining speech models for end-to-end spoken language understanding. We show that our models reach higher performance over baselines on monolingual and multilingual intent classification. We also create new benchmark datasets for speech summarization and low-resource/zero-shot transfer from English to French or Spanish.
  arXiv  Detail & Related papers  (2023-05-16T17:53:03Z)
• MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition [51.412413996510814]
  We propose MixSpeech, a cross-modality self-learning framework that utilizes audio speech to regularize the training of visual speech tasks. MixSpeech enhances speech translation in noisy environments, improving BLEU scores for four languages on AVMuST-TED by +1.4 to +4.2.
  arXiv  Detail & Related papers  (2023-03-09T14:58:29Z)
• 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)
• Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding [55.989376102986654]
  This paper studies a transferable phoneme embedding framework that aims to deal with the cross-lingual text-to-speech problem under the few-shot setting. We propose a framework that consists of a phoneme-based TTS model and a codebook module to project phonemes from different languages into a learned latent space.
  arXiv  Detail & Related papers  (2022-06-27T11:24:40Z)
• Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity [81.51206991542242]
  Cross-lingual transfer offers a compelling way to help bridge this digital divide. Current cross-lingual algorithms have shown success in text-based tasks and speech-related tasks over some low-resource languages. We propose a language similarity approach that can efficiently identify acoustic cross-lingual transfer pairs across hundreds of languages.
  arXiv  Detail & Related papers  (2021-11-02T01:55:17Z)
• Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation [53.22775597051498]
  We present a continual pre-training framework on mBART to effectively adapt it to unseen languages. Results show that our method can consistently improve the fine-tuning performance upon the mBART baseline. Our approach also boosts the performance on translation pairs where both languages are seen in the original mBART's pre-training.
  arXiv  Detail & Related papers  (2021-05-09T14:49:07Z)
• Consecutive Decoding for Speech-to-text Translation [51.155661276936044]
  COnSecutive Transcription and Translation (COSTT) is an integral approach for speech-to-text translation. The key idea is to generate source transcript and target translation text with a single decoder. Our method is verified on three mainstream datasets.
  arXiv  Detail & Related papers  (2020-09-21T10:10:45Z)

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.