Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cadet, Xavier F., Aloufi, Ranya, Ahmadi-Abhari, Sara, Haddadi, Hamed
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2306.04337
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914725371052032
author Cadet, Xavier F.
Aloufi, Ranya
Ahmadi-Abhari, Sara
Haddadi, Hamed
author_facet Cadet, Xavier F.
Aloufi, Ranya
Ahmadi-Abhari, Sara
Haddadi, Hamed
contents Automating dysarthria assessments offers the opportunity to develop practical, low-cost tools that address the current limitations of manual and subjective assessments. Nonetheless, the small size of most dysarthria datasets makes it challenging to develop automated assessment. Recent research showed that speech representations from models pre-trained on large unlabelled data can enhance Automatic Speech Recognition (ASR) performance for dysarthric speech. We are the first to evaluate the representations from pre-trained state-of-the-art Self-Supervised models across three downstream tasks on dysarthric speech: disease classification, word recognition and intelligibility classification, and under three noise scenarios on the UA-Speech dataset. We show that HuBERT is the most versatile feature extractor across dysarthria classification, word recognition, and intelligibility classification, achieving respectively $+24.7\%, +61\%, \text{and} +7.2\%$ accuracy compared to classical acoustic features.
format Preprint
id arxiv_https___arxiv_org_abs_2306_04337
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment
Cadet, Xavier F.
Aloufi, Ranya
Ahmadi-Abhari, Sara
Haddadi, Hamed
Computation and Language
Automating dysarthria assessments offers the opportunity to develop practical, low-cost tools that address the current limitations of manual and subjective assessments. Nonetheless, the small size of most dysarthria datasets makes it challenging to develop automated assessment. Recent research showed that speech representations from models pre-trained on large unlabelled data can enhance Automatic Speech Recognition (ASR) performance for dysarthric speech. We are the first to evaluate the representations from pre-trained state-of-the-art Self-Supervised models across three downstream tasks on dysarthric speech: disease classification, word recognition and intelligibility classification, and under three noise scenarios on the UA-Speech dataset. We show that HuBERT is the most versatile feature extractor across dysarthria classification, word recognition, and intelligibility classification, achieving respectively $+24.7\%, +61\%, \text{and} +7.2\%$ accuracy compared to classical acoustic features.
title A study on the impact of Self-Supervised Learning on automatic dysarthric speech assessment
topic Computation and Language
url https://arxiv.org/abs/2306.04337