[2603.02252] Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics

Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2603.02252 (eess) [Submitted on 27 Feb 2026] Title:Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics Authors:Mandip Goswami View a PDF of the paper titled Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics, by Mandip Goswami View PDF HTML (experimental) Abstract:We introduce Whisper-RIR-Mega, a benchmark dataset of paired clean and reverberant speech for evaluating automatic speech recognition (ASR) robustness to room acoustics. Each sample pairs a clean LibriSpeech utterance with the same utterance convolved with a real room impulse response from the RIR-Mega corpus, with stratified splits by reverberation time (RT60) and direct-to-reverberant ratio (DRR). We evaluate five Whisper models (tiny through large-v3) on 1600 test samples and report word error rate (WER) and character error rate (CER) under clean and reverberant conditions. Reverberation consistently degrades performance across all model sizes; the reverb penalty in WER ranges from 0.12 to 1.07 percentage points depending on the model. We release the dataset, evaluation code, and baseline results to support reproducible research on robust ASR. Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD) Cite as: arXiv:2603.02252 [eess.AS]   (or arXiv:2603.02252v1 [eess.AS] for th...