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
This work addresses speech translation for low-resource Indic languages, presenting an incremental improvement by combining existing models.
The paper tackled speech-to-text translation for English-Indic language pairs in a low-resource scenario by integrating the Whisper ASR model with the Krutrim Indic LLM, achieving average BLEU scores of 28.88 for English-to-Indic and 27.86 for Indic-to-English. It also explored the Chain-of-Thought method, which showed potential for large improvements (e.g., a 13.84 BLEU increase for Tamil-to-English) but faced challenges in consistent output formatting.
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.