paper-with-me

홈 › Papers

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

2026-02-27 · Mandip Goswami arxiv

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 2.31 to 15.50 percentage points depending on the model. Whisper-large-v3 shows the smallest penalty; Whisper-tiny shows the largest. We release the dataset, evaluation code, and baseline results to support reproducible research on robust ASR.

📄 PDF Abstract BibTeX arXiv:2603.02252

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

RIR-Mega-Speech: A Reverberant Speech Corpus with Comprehensive Acoustic Metadata and Reproducible Evaluation

2026-01-25 · Mandip Goswami arxiv

Despite decades of research on reverberant speech, comparing methods remains difficult because most corpora lack per-file acoustic annotations or provide limited documentation for reproduction. We present RIR-Mega-Speech…

Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation

2022-10-24 · Marvin Lavechin, Marianne Métais, Hadrien Titeux, Alodie Boissonnet 외

Most automatic speech processing systems register degraded performance when applied to noisy or reverberant speech. But how can one tell whether speech is noisy or reverberant? We propose Brouhaha, a neural network joint…

Action DetectionActivity DetectionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)+2

Advancing NAM-to-Speech Conversion with Novel Methods and the MultiNAM Dataset

2024-12-25 · Neil Shah, Shirish Karande, Vineet Gandhi

Current Non-Audible Murmur (NAM)-to-speech techniques rely on voice cloning to simulate ground-truth speech from paired whispers. However, the simulated speech often lacks intelligibility and fails to generalize well acr…

text-to-speechText to SpeechVoice Cloning

A processing framework to access large quantities of whispered speech found in ASMR

2023-03-13 · Pablo Perez Zarazaga, Gustav Eje Henter, Zofia Malisz

Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To re…

Action DetectionActivity Detection

Treble10: A high-quality dataset for far-field speech recognition, dereverberation, and enhancement

2025-10-27 · Sarabeth S. Mullins, Georg Götz, Eric Bezzam, Steven Zheng 외 arxiv

Accurate far-field speech datasets are critical for tasks such as automatic speech recognition (ASR), dereverberation, speech enhancement, and source separation. However, current datasets are limited by the trade-off bet…

Speech RecognitionSpeech EnhancementData Augmentation