PaperScope
LIVE · 2026-09-22 05:40 UTC

Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations

Kaushal Santosh Bhogale, Srija Anand, Sadakopa Ramakrishnan Thothathiri, Tahir Javed, Sshubam Verma, Mitesh M. Khapra

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.24199 v1
Category
Submitted
2026-09-21

Abstract

Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlled audio conditions, and pessimistic scores from overly rigid transcription standards that penalize valid linguistic variations. We introduce Vimarsha, a 100-hour benchmark spanning all 22 scheduled Indian languages, designed to address both distortions. Vimarsha combines demographically diverse on-field recordings with carefully mined in-the-wild audio selected for acoustic difficulty, alongside a lattice of variations framework that encodes multiple valid transcriptions per utterance. Evaluations of 10 state-of-the-art ASR models reveal substantial shifts in model rankings under realistic conditions, geographic and demographic performance disparities, and systematic failure modes across speaking rates and acoustic environments.

Comment: Accepted in Interspeech 2026

arXiv abs page · PDF · same-day batch