OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking
This dataset addresses the need for robust ASR systems in Bengali, a widely spoken language with high dialectal diversity, by providing a benchmark for evaluating performance under distribution shifts.
The authors introduced OOD-Speech, the first out-of-distribution benchmarking dataset for Bengali automatic speech recognition, comprising 1177.94 hours of training data from 22,645 speakers and 23.03 hours of test data from diverse sources like TV dramas and Islamic sermons.
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.