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
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909706376708096 |
|---|---|
| author | Wei, Xuchen Wu, Yangxin Zhang, Yaoyin Liu, Henglyu Chen, Kehai Bai, Xuefeng Zhang, Min |
| author_facet | Wei, Xuchen Wu, Yangxin Zhang, Yaoyin Liu, Henglyu Chen, Kehai Bai, Xuefeng Zhang, Min |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19616 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 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 Wei, Xuchen Wu, Yangxin Zhang, Yaoyin Liu, Henglyu Chen, Kehai Bai, Xuefeng Zhang, Min Computation and Language 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. |
| title | 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 |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.19616 |