Speech foundation models on intelligibility prediction for hearing-impaired listeners

Abstract

Speech foundation models (SFMs) have been benchmarked on many speech processing tasks, often achieving state-of-the-art performance with minimal adaptation. However, the SFM paradigm has been significantly less explored for applications of interest to the speech perception community. In this paper we present a systematic evaluation of 10 SFMs on one such application: Speech intelligibility prediction. We focus on the non-intrusive setup of the Clarity Prediction Challenge 2 (CPC2), where the task is to predict the percentage of words correctly perceived by hearing-impaired listeners from speech-in-noise recordings. We propose a simple method that learns a lightweight specialized prediction head on top of frozen SFMs to approach the problem. Our results reveal statistically significant differences in performance across SFMs. Our method resulted in the winning submission in the CPC2, demonstrating its promise for speech perception applications.

To be presented in ICASSP 2024

References in corpus (4)

• Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
• The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
• Clarity: Machine Learning Challenges to Revolutionise Hearing Device Processing
• Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations