Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.13431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917702858178560 |
|---|---|
| author | Sukhadia, Vrunda N. Chowdhury, Shammur Absar |
| author_facet | Sukhadia, Vrunda N. Chowdhury, Shammur Absar |
| contents | Children's speech recognition is considered a low-resource task mainly due to the lack of publicly available data. There are several reasons for such data scarcity, including expensive data collection and annotation processes, and data privacy, among others. Transforming speech signals into discrete tokens that do not carry sensitive information but capture both linguistic and acoustic information could be a solution for privacy concerns. In this study, we investigate the integration of discrete speech tokens into children's speech recognition systems as input without significantly degrading the ASR performance. Additionally, we explored single-view and multi-view strategies for creating these discrete labels. Furthermore, we tested the models for generalization capabilities with unseen domain and nativity dataset. Results reveal that the discrete token ASR for children achieves nearly equivalent performance with an approximate 83% reduction in parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13431 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Children's Speech Recognition through Discrete Token Enhancement Sukhadia, Vrunda N. Chowdhury, Shammur Absar Computation and Language Sound Audio and Speech Processing Children's speech recognition is considered a low-resource task mainly due to the lack of publicly available data. There are several reasons for such data scarcity, including expensive data collection and annotation processes, and data privacy, among others. Transforming speech signals into discrete tokens that do not carry sensitive information but capture both linguistic and acoustic information could be a solution for privacy concerns. In this study, we investigate the integration of discrete speech tokens into children's speech recognition systems as input without significantly degrading the ASR performance. Additionally, we explored single-view and multi-view strategies for creating these discrete labels. Furthermore, we tested the models for generalization capabilities with unseen domain and nativity dataset. Results reveal that the discrete token ASR for children achieves nearly equivalent performance with an approximate 83% reduction in parameters. |
| title | Children's Speech Recognition through Discrete Token Enhancement |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.13431 |