# 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: https://arxiv.org/abs/2507.19616 · HTML: https://mlsanity.com/paper/2507.19616/

## 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 (most cited first, 15 of 15)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [fairseq S2T: Fast Speech-to-Text Modeling with fairseq](https://mlsanity.com/paper/2010.05171/) (2020)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [Pre-training on high-resource speech recognition improves low-resource speech-to-text translation](https://mlsanity.com/paper/1809.01431/) (2018)
- [End-to-End Automatic Speech Translation of Audiobooks](https://mlsanity.com/paper/1802.04200/) (2018)
- [Bridging the Modality Gap for Speech-to-Text Translation](https://mlsanity.com/paper/2010.14920/) (2020)
- [IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages](https://mlsanity.com/paper/2403.01926/) (2024)
- [Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation](https://mlsanity.com/paper/2004.10171/) (2020)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [Pushing the Limits of Zero-shot End-to-End Speech Translation](https://mlsanity.com/paper/2402.10422/) (2024)
- [MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation](https://mlsanity.com/paper/2412.07147/) (2024)
- [Krutrim LLM: Multilingual Foundational Model for over a Billion People](https://mlsanity.com/paper/2502.09642/) (2025)

## 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.