Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917265922850816 |
|---|---|
| author | Dhasmana, Akriti Srivastava, Aarohi Chiang, David |
| author_facet | Dhasmana, Akriti Srivastava, Aarohi Chiang, David |
| contents | We conduct an empirical study of cross-lingual transfer using spontaneous, noisy, and code-mixed speech across a wide range of Indic dialects and language varieties. Our results indicate that although ASR performance is generally improved with reduced phylogenetic distance between languages, this factor alone does not fully explain performance in dialectal settings. Often, fine-tuning on smaller amounts of dialectal data yields performance comparable to fine-tuning on larger amounts of phylogenetically-related, high-resource standardized languages. We also present a case study on Garhwali, a low-resource Pahari language variety, and evaluate multiple contemporary ASR models. Finally, we analyze transcription errors to examine bias toward pre-training languages, providing additional insight into challenges faced by ASR systems on dialectal and non-standardized speech. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04373 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties Dhasmana, Akriti Srivastava, Aarohi Chiang, David Computation and Language I.2.7 We conduct an empirical study of cross-lingual transfer using spontaneous, noisy, and code-mixed speech across a wide range of Indic dialects and language varieties. Our results indicate that although ASR performance is generally improved with reduced phylogenetic distance between languages, this factor alone does not fully explain performance in dialectal settings. Often, fine-tuning on smaller amounts of dialectal data yields performance comparable to fine-tuning on larger amounts of phylogenetically-related, high-resource standardized languages. We also present a case study on Garhwali, a low-resource Pahari language variety, and evaluate multiple contemporary ASR models. Finally, we analyze transcription errors to examine bias toward pre-training languages, providing additional insight into challenges faced by ASR systems on dialectal and non-standardized speech. |
| title | Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2601.04373 |