Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918151064649728 |
|---|---|
| author | Cheng, Yao-Fei Chen, Li-Wei Lee, Hung-Shin Wang, Hsin-Min |
| author_facet | Cheng, Yao-Fei Chen, Li-Wei Lee, Hung-Shin Wang, Hsin-Min |
| contents | This study investigates the efficacy of data augmentation techniques for low-resource automatic speech recognition (ASR), focusing on two endangered Austronesian languages, Amis and Seediq. Recognizing the potential of self-supervised learning (SSL) in low-resource settings, we explore the impact of data volume on the continued pre-training of SSL models. We propose a novel data-selection scheme leveraging a multilingual corpus to augment the limited target language data. This scheme utilizes a language classifier to extract utterance embeddings and employs one-class classifiers to identify utterances phonetically and phonologically proximate to the target languages. Utterances are ranked and selected based on their decision scores, ensuring the inclusion of highly relevant data in the SSL-ASR pipeline. Our experimental results demonstrate the effectiveness of this approach, yielding substantial improvements in ASR performance for both Amis and Seediq. These findings underscore the feasibility and promise of data augmentation through cross-lingual transfer learning for low-resource language ASR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08872 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages Cheng, Yao-Fei Chen, Li-Wei Lee, Hung-Shin Wang, Hsin-Min Computation and Language Sound Audio and Speech Processing This study investigates the efficacy of data augmentation techniques for low-resource automatic speech recognition (ASR), focusing on two endangered Austronesian languages, Amis and Seediq. Recognizing the potential of self-supervised learning (SSL) in low-resource settings, we explore the impact of data volume on the continued pre-training of SSL models. We propose a novel data-selection scheme leveraging a multilingual corpus to augment the limited target language data. This scheme utilizes a language classifier to extract utterance embeddings and employs one-class classifiers to identify utterances phonetically and phonologically proximate to the target languages. Utterances are ranked and selected based on their decision scores, ensuring the inclusion of highly relevant data in the SSL-ASR pipeline. Our experimental results demonstrate the effectiveness of this approach, yielding substantial improvements in ASR performance for both Amis and Seediq. These findings underscore the feasibility and promise of data augmentation through cross-lingual transfer learning for low-resource language ASR. |
| title | Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.08872 |