Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context

arXiv:2403.20184v1 Announce Type: cross
Abstract: Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification, largely due to data scarcity. To deal with this challenge, current works tend to segment patients' audio files into many samples to augment the datasets. Nevertheless, this approach has limitations, as it indirectly relates overall audio scores to individual segments. This …

abstract arxiv asr assessment attention binary challenge classification clinical context cs.cl cs.lg cs.sd data deal eess.as evaluation good however quality research results simple speech support tasks type wav2vec2