mlsanityData to 14 Oct 2026

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track

arXiv 2507.19616 ↗First posted 25 Jul 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents HITSZ's submission for the IWSLT 2025 Indic track, focusing on speech-to-text translation (ST) for English-to-Indic and Indic-to-English language pairs. To enhance translation quality in this low-resource scenario, we propose an end-to-end system integrating the pre-trained Whisper automated speech recognition (ASR) model with Krutrim, an Indic-specialized large language model (LLM). Experimental results demonstrate that our end-to-end system achieved average BLEU scores of 28.88 for English-to-Indic directions and 27.86 for Indic-to-English directions. Furthermore, we investigated the Chain-of-Thought (CoT) method. While this method showed potential for significant translation quality improvements on successfully parsed outputs (e.g. a 13.84 BLEU increase for Tamil-to-English), we observed challenges in ensuring the model consistently adheres to the required CoT output format.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

15 of 27 references.

References · 15

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  3. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 388
  4. 2020fairseq S2T: Fast Speech-to-Text Modeling with fairseqcited by 176
  5. 2023IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languagescited by 152
  6. 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
  7. 2018Pre-training on high-resource speech recognition improves low-resource speech-to-text translationcited by 70
  8. 2018End-to-End Automatic Speech Translation of Audiobookscited by 65
  9. 2020Bridging the Modality Gap for Speech-to-Text Translationcited by 55
  10. 2024IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languagescited by 41
  11. 2020Knowledge Distillation for Multilingual Unsupervised Neural Machine Translationcited by 19
  12. 2023Recent Advances in Direct Speech-to-text Translationcited by 15
3 more
  1. 2024Pushing the Limits of Zero-shot End-to-End Speech Translationcited by 14
  2. 2024MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translationcited by 12
  3. 2025Krutrim LLM: Multilingual Foundational Model for over a Billion Peoplecited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Speech Translation with Large Language Models: An Industrial Practice
  2. 2021The USYD-JD Speech Translation System for IWSLT 2021
  3. 2024Anatomy of Industrial Scale Multilingual ASR
  4. 2023Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
  5. 2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  6. 2025MLMA: Towards Multilingual ASR With Mamba-based Architectures
  7. 2021Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders
  8. 2023Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition