Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?

Tawsif Tashwar Dipto, Azmol Hossain, Rubayet Sabbir Faruque, Md. Rezuwan Hassan, Kanij Fatema +10 more
10/27/2025
cs.CL

No confident code implementation found for this paper.

Abstract

Conventional research on speech recognition modeling relies on the canonical form for most low-resource languages while automatic speech recognition (ASR) for regional dialects is treated as a fine-tuning task. To investigate the effects of dialectal variations on ASR we develop a 78-hour annotated Bengali Speech-to-Text (STT) corpus named Ben-10. Investigation from linguistic and data-driven perspectives shows that speech foundation models struggle heavily in regional dialect ASR, both in zero-shot and fine-tuned settings. We observe that all deep learning methods struggle to model speech data under dialectal variations but dialect specific model training alleviates the issue. Our dataset also serves as a out of-distribution (OOD) resource for ASR modeling under constrained resources in ASR algorithms. The dataset and code developed for this project are publicly available

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization

86% match1 repo32024

Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties

85% match2026

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe

85% match1 repo482025

Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages

85% match2025

RegSpeech12: A Regional Corpus of Bengali Spontaneous Speech Across Dialects

85% match2025

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla

85% match2025

Cite this paper

@article{dipto2025foundation,
  title  = {Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?},
  author = {Tawsif Tashwar Dipto and Azmol Hossain and Rubayet Sabbir Faruque and Md. Rezuwan Hassan and Kanij Fatema and Tanmoy Shome and Ruwad Naswan and Md. Foriduzzaman Zihad and Mohaymen Ul Anam and Nazia Tasnim and Hasan Mahmud and Md Kamrul Hasan and Md. Mehedi Hasan Shawon and Farig Sadeque and Tahsin Reasat},
  year   = {2025},
  eprint = {2510.23252},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.23252v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.23252.svg)](https://codeofpaper.com/paper/2510.23252)

Discussion