Speech foundation models on intelligibility prediction for hearing-impaired listeners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cuervo, Santiago, Marxer, Ricard
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916389984403456
author Cuervo, Santiago
Marxer, Ricard
author_facet Cuervo, Santiago
Marxer, Ricard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14289
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Speech foundation models on intelligibility prediction for hearing-impaired listeners
Cuervo, Santiago
Marxer, Ricard
Sound
Machine Learning
Audio and Speech Processing
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.
title Speech foundation models on intelligibility prediction for hearing-impaired listeners
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2401.14289