mlsanityData to 7 Oct 2026

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

arXiv 2305.09688 ↗First posted 15 May 2023eess.AS cs.CL cs.LGcited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 8 of its 45 references that are in the map. First posted on arXiv 15 May 2023.

Builds on

8 of 45 references.

References · 8

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  3. 2014Distributed Representations of Sentences and Documentscited by 677
  4. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  5. 2020Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Trainingcited by 38
  6. 2022Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languagescited by 16
  7. 2020A Large Multi-Target Dataset of Common Bengali Handwritten Graphemescited by 12
  8. 2022Applying wav2vec2 for Speech Recognition on Bengali Common Voices Datasetcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 3.

6 papers.

  1. 2023Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognitioncited by 4
  2. 2025RegSpeech12: A Regional Corpus of Bengali Spontaneous Speech Across Dialectscited by 2
  3. 2025Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?cited by 1
  4. 2024Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognitioncited by 0
  5. 2024Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identificationcited by 0
  6. 2025Evaluating and Improving the Robustness of Speech Command Recognition Models to Noise and Distribution Shiftscited by 0