Attention-Guided Adaptation for Code-Switching Speech Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910294946611200 |
|---|---|
| author | Aditya, Bobbi Rohmatillah, Mahdin Tai, Liang-Hsuan Chien, Jen-Tzung |
| author_facet | Aditya, Bobbi Rohmatillah, Mahdin Tai, Liang-Hsuan Chien, Jen-Tzung |
| contents | The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in multilingual speech recognition. Recent studies have attempted to address this setting by separating the modules for different languages to ensure distinct latent representations for languages. Some other methods considered the switching mechanism based on language identification. In this study, a new attention-guided adaptation is proposed to conduct parameter-efficient learning for bilingual ASR. This method selects those attention heads in a model which closely express language identities and then guided those heads to be correctly attended with their corresponding languages. The experiments on the Mandarin-English code-switching speech corpus show that the proposed approach achieves a 14.2% mixed error rate, surpassing state-of-the-art method, where only 5.6% additional parameters over Whisper are trained. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_08856 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Attention-Guided Adaptation for Code-Switching Speech Recognition Aditya, Bobbi Rohmatillah, Mahdin Tai, Liang-Hsuan Chien, Jen-Tzung Audio and Speech Processing Sound The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition. However, these models often struggle with handling the code-switching setting, which is essential in multilingual speech recognition. Recent studies have attempted to address this setting by separating the modules for different languages to ensure distinct latent representations for languages. Some other methods considered the switching mechanism based on language identification. In this study, a new attention-guided adaptation is proposed to conduct parameter-efficient learning for bilingual ASR. This method selects those attention heads in a model which closely express language identities and then guided those heads to be correctly attended with their corresponding languages. The experiments on the Mandarin-English code-switching speech corpus show that the proposed approach achieves a 14.2% mixed error rate, surpassing state-of-the-art method, where only 5.6% additional parameters over Whisper are trained. |
| title | Attention-Guided Adaptation for Code-Switching Speech Recognition |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2312.08856 |