cs.CLJun 28, 2026

Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs

Authors: Nithin Rao KoluguriSasha MeisterNikolay KarpovPiotr ZelaskoDesh RajJagadeesh BalamBoris Ginsburg

Organizations: NVIDIA, USA

Abstract

Popular ASR test sets adopt inconsistent conventions for numbers, disfluencies, entities, and casing, while standard normalizers erase the format distinctions users care about. Current benchmarks therefore cannot measure whether a model follows user preferences for output style. We introduce PreferenceASR, a test set evaluating ASR systems on their ability to follow natural-language preference instructions across four categories: normalization, entities, disfluencies, and case. Built from seven open-source corpora via a two-stage LLM-assisted pipeline with human verification, it is evaluated with a preference-aware normalizer that selectively skips steps matching the active instruction. Benchmarking four models shows rankings shift across preference types, exposing quality differences traditional evaluation obscures. We publicly release the dataset.

Explore similar work

CardsList