Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916313262194688 |
|---|---|
| author | Sildam, Tiia Velve, Andra Alumäe, Tanel |
| author_facet | Sildam, Tiia Velve, Andra Alumäe, Tanel |
| contents | This paper investigates the finetuning of end-to-end models for bidirectional Estonian-English and Estonian-Russian conversational speech-to-text translation. Due to the limited availability of speech translation data for Estonian, we created additional training data by web scraping and synthesizing data from speech recognition datasets using machine translation. We evaluated three publicly available end-to-end models: Whisper, OWSM 3.1, and SeamlessM4T. Our results indicate that fine-tuning with synthetic data enhances translation accuracy by a large margin, with SeamlessM4T matching or surpassing cascaded speech translation systems that use state-of-the-art speech recognition and machine translation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03809 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation Sildam, Tiia Velve, Andra Alumäe, Tanel Computation and Language Audio and Speech Processing This paper investigates the finetuning of end-to-end models for bidirectional Estonian-English and Estonian-Russian conversational speech-to-text translation. Due to the limited availability of speech translation data for Estonian, we created additional training data by web scraping and synthesizing data from speech recognition datasets using machine translation. We evaluated three publicly available end-to-end models: Whisper, OWSM 3.1, and SeamlessM4T. Our results indicate that fine-tuning with synthetic data enhances translation accuracy by a large margin, with SeamlessM4T matching or surpassing cascaded speech translation systems that use state-of-the-art speech recognition and machine translation models. |
| title | Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.03809 |