Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916913985093632 |
|---|---|
| author | Wang, Qingzheng Shim, Hye-jin Sun, Jiancheng Watanabe, Shinji |
| author_facet | Wang, Qingzheng Shim, Hye-jin Sun, Jiancheng Watanabe, Shinji |
| contents | While Self-supervised Learning (SSL) has significantly improved Spoken Language Identification (LID), existing models often struggle to consistently classify dialects and accents of the same language as a unified class. To address this challenge, we propose geolocation-aware LID, a novel approach that incorporates language-level geolocation information into the SSL-based LID model. Specifically, we introduce geolocation prediction as an auxiliary task and inject the predicted vectors into intermediate representations as conditioning signals. This explicit conditioning encourages the model to learn more unified representations for dialectal and accented variations. Experiments across six multilingual datasets demonstrate that our approach improves robustness to intra-language variations and unseen domains, achieving new state-of-the-art accuracy on FLEURS (97.7%) and 9.7% relative improvement on ML-SUPERB 2.0 dialect set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17148 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Geolocation-Aware Robust Spoken Language Identification Wang, Qingzheng Shim, Hye-jin Sun, Jiancheng Watanabe, Shinji Computation and Language Sound While Self-supervised Learning (SSL) has significantly improved Spoken Language Identification (LID), existing models often struggle to consistently classify dialects and accents of the same language as a unified class. To address this challenge, we propose geolocation-aware LID, a novel approach that incorporates language-level geolocation information into the SSL-based LID model. Specifically, we introduce geolocation prediction as an auxiliary task and inject the predicted vectors into intermediate representations as conditioning signals. This explicit conditioning encourages the model to learn more unified representations for dialectal and accented variations. Experiments across six multilingual datasets demonstrate that our approach improves robustness to intra-language variations and unseen domains, achieving new state-of-the-art accuracy on FLEURS (97.7%) and 9.7% relative improvement on ML-SUPERB 2.0 dialect set. |
| title | Geolocation-Aware Robust Spoken Language Identification |
| topic | Computation and Language Sound |
| url | https://arxiv.org/abs/2508.17148 |