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

• URL: http://arxiv.org/abs/2510.23252v2
• Date: Wed, 29 Oct 2025 09:41:26 GMT
• Title: Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?
• Authors: Tawsif Tashwar Dipto, Azmol Hossain, Rubayet Sabbir Faruque, Md. Rezuwan Hassan, Kanij Fatema, Tanmoy Shome, Ruwad Naswan, Md. Foriduzzaman Zihad, Mohaymen Ul Anam, Nazia Tasnim, Hasan Mahmud, Md Kamrul Hasan, Md. Mehedi Hasan Shawon, Farig Sadeque, Tahsin Reasat,
• Abstract summary: We develop a 78-hour annotated Bengali Speech-to-Text (STT) corpus named Ben-10.<n>Investigation from linguistic and data-driven perspectives shows that speech foundation models struggle heavily in regional dialect ASR.<n>We observe that all deep learning methods struggle to model speech data under dialectal variations but dialect specific model training alleviates the issue.
• Score: 3.703726003145388
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• WESR: Scaling and Evaluating Word-level Event-Speech Recognition [59.21814194620928]
  Speech conveys not only linguistic information but also rich non-verbal vocal events such as laughing and crying.<n>We develop a refined taxonomy of 21 vocal events, with a new categorization into discrete (standalone) versus continuous (mixed with speech) types.<n>Based on the refined taxonomy, we introduce WESR-Bench, an expert-annotated evaluation set (900+ utterances) with a novel position-aware protocol.
  arXiv  Detail & Related papers  (2026-01-08T02:23:21Z)
• Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties [7.81142462208334]
  We conduct an empirical study of cross-lingual transfer using spontaneous, noisy, and code-mixed speech.<n>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.
  arXiv  Detail & Related papers  (2026-01-07T20:31:05Z)
• Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages [76.14451035425229]
  We introduce Omnilingual ASR, a large-scale automatic speech recognition system.<n>It scales self-supervised pre-training to 7B parameters to learn robust speech representations.<n>It expands coverage to over 1,600 languages, including over 500 never before served by ASR.
  arXiv  Detail & Related papers  (2025-11-12T19:48:09Z)
• Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet [72.53502346791814]
  We compare flat-start training across datasets, SSL representations (WavLM, XEUS), and decoder architectures.<n> SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases.<n>Age-related ASR and speaker verification analysis highlights the limitations of proprietary models.
  arXiv  Detail & Related papers  (2025-08-22T17:59:35Z)
• A Cookbook for Community-driven Data Collection of Impaired Speech in LowResource Languages [7.883772614704979]
  This study presents an approach for collecting speech samples to build Automatic Speech Recognition models for impaired speech.<n>It aims to democratize ASR technology and data collection by developing a "cookbook" of best practices and training for community-driven data collection and ASR model building.<n>As a proof-of-concept, this study curated the first open-source dataset of impaired speech in Akan: a widely spoken indigenous language in Ghana.
  arXiv  Detail & Related papers  (2025-07-03T08:34:15Z)
• MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models [59.80042864360884]
  Speaker-attributed automatic speech recognition (SA-ASR) aims to transcribe speech while assigning transcripts to the corresponding speakers accurately.<n>This paper introduces a novel approach, leveraging a frozen multilingual ASR model to incorporate speaker attribution into the transcriptions.
  arXiv  Detail & Related papers  (2024-11-27T09:01:08Z)
• Enabling ASR for Low-Resource Languages: A Comprehensive Dataset Creation Approach [0.6445605125467574]
  This study introduces a novel pipeline designed to generate ASR training datasets from audiobooks. The common structure of these audiobooks poses a unique challenge due to the extensive length of audio segments. We propose a method for effectively aligning audio with its corresponding text and segmenting it into lengths suitable for ASR training.
  arXiv  Detail & Related papers  (2024-06-03T15:38:40Z)
• Multilingual acoustic word embeddings for zero-resource languages [1.5229257192293204]
  It specifically uses acoustic word embedding (AWE) -- fixed-dimensional representations of variable-duration speech segments. The study introduces a new neural network that outperforms existing AWE models on zero-resource languages. AWEs are applied to a keyword-spotting system for hate speech detection in Swahili radio broadcasts.
  arXiv  Detail & Related papers  (2024-01-19T08:02:37Z)
• Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili [16.424308444697015]
  We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to build an automatic speech recognition system for the target low-resource language. We compare this to using acoustic word embedding models that map speech segments to a space where matching words have similar vectors.
  arXiv  Detail & Related papers  (2023-06-01T07:25:10Z)
• A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition [80.87085897419982]
  We propose a novel acoustic modeling technique for accurate multi-dialect speech recognition with a single AM. Our proposed AM is dynamically adapted based on both dialect information and its internal representation, which results in a highly adaptive AM for handling multiple dialects simultaneously. The experimental results on large scale speech datasets show that the proposed AM outperforms all the previous ones, reducing word error rates (WERs) by 8.11% relative compared to a single all-dialects AM and by 7.31% relative compared to dialect-specific AMs.
  arXiv  Detail & Related papers  (2022-05-06T06:07:09Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.