# OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking

arXiv: https://arxiv.org/abs/2305.09688 · HTML: https://mlsanity.com/paper/2305.09688/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 8 of 8)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Understanding Failures in Out-of-Distribution Detection with Deep Generative Models](https://mlsanity.com/paper/2107.06908/) (2021)
- [Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training](https://mlsanity.com/paper/2011.13439/) (2020)
- [Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages](https://mlsanity.com/paper/2208.12666/) (2022)
- [A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes](https://mlsanity.com/paper/2010.00170/) (2020)
- [Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset](https://mlsanity.com/paper/2209.06581/) (2022)

## Built on by (most cited first, 9 of 9)

- [Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognition](https://mlsanity.com/paper/2311.03196/) (2023)
- [RegSpeech12: A Regional Corpus of Bengali Spontaneous Speech Across Dialects](https://mlsanity.com/paper/2510.24096/) (2025)
- [Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?](https://mlsanity.com/paper/2510.23252/) (2025)
- [BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources](https://mlsanity.com/paper/2604.18423/) (2026)
- [Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognition](https://mlsanity.com/paper/2401.15532/) (2024)
- [Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification](https://mlsanity.com/paper/2406.18067/) (2024)
- [Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shifts](https://mlsanity.com/paper/2507.23128/) (2025)
- [When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews](https://mlsanity.com/paper/2606.24244/) (2026)
- [Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR](https://mlsanity.com/paper/2607.09598/) (2026)

## Abstract (arXiv)

We present OOD-Speech, the first out-of-distribution (OOD) benchmarking dataset for Bengali automatic speech recognition (ASR). Being one of the most spoken languages globally, Bengali portrays large diversity in dialects and prosodic features, which demands ASR frameworks to be robust towards distribution shifts. For example, islamic religious sermons in Bengali are delivered with a tonality that is significantly different from regular speech. Our training dataset is collected via massively online crowdsourcing campaigns which resulted in 1177.94 hours collected and curated from 22,645 native Bengali speakers from South Asia. Our test dataset comprises 23.03 hours of speech collected and manually annotated from 17 different sources, e.g., Bengali TV drama, Audiobook, Talk show, Online class, and Islamic sermons to name a few. OOD-Speech is jointly the largest publicly available speech dataset, as well as the first out-of-distribution ASR benchmarking dataset for Bengali.