OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Automatic Assessment of Speech Capability Loss in Disordered Speech

Pellegrini, Thomas and Fontan, Lionel and Mauclair, Julie and Farinas, Jérome and Alazard-Guiu, Charlotte and Robert, Marina and Gatignol, Peggy Automatic Assessment of Speech Capability Loss in Disordered Speech. (2015) ACM Transactions on Accessible Computing (TACCESS) - Special Issue on Speech and Language Processing for AT (Part 1), 6 (3). 1-14. ISSN 1936-7228

(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1145/2739051


In this article, we report on the use of an automatic technique to assess pronunciation in the context of several types of speech disorders. Even if such tools already exist, they are more widely used in a different context, namely, Computer-Assisted Language Learning, in which the objective is to assess nonnative pronunciation by detecting learners' mispronunciations at segmental and/or suprasegmental levels. In our work, we sought to determine if the Goodness of Pronunciation (GOP) algorithm, which aims to detect phone-level mispronunciations by means of automatic speech recognition, could also detect segmental deviances in disordered speech. Our main experiment is an analysis of speech from people with unilateral facial palsy. This pathology may impact the realization of certain phonemes such as bilabial plosives and sibilants. Speech read by 32 speakers at four different clinical severity grades was automatically aligned and GOP scores were computed for each phone realization. The highest scores, which indicate large dissimilarities with standard phone realizations, were obtained for the most severely impaired speakers. The corresponding speech subset was manually transcribed at phone level; 8.3% of the phones differed from standard pronunciations extracted from our lexicon. The GOP technique allowed the detection of 70.2% of mispronunciations with an equal rate of about 30% of false rejections and false acceptances. Finally, to broaden the scope of the study, we explored the correlation between GOP values and speech comprehensibility scores on a second corpus, composed of sentences recorded by six people with speech impairments due to cancer surgery or neurological disorders. Strong correlations were achieved between GOP scores and subjective comprehensibility scores (about 0.7 absolute). Results from both experiments tend to validate the use of GOP to measure speech capability loss, a dimension that could be used as a complement to physiological measures in pathologies causing speech disorders.

Item Type:Article
Additional Information:Thanks to ACM editor. The definitive version is available at http://dl.acm.org The original PDF of the article can be found at ACM Transactions on Accessible Computing (TACCESS) website : http://dl.acm.org/citation.cfm?id=2739051 Special Issue on Speech and Language Processing for AT (Part 1) ISSN: 1936-7228 ESSN: 1936-7236
HAL Id:hal-01371812
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
French research institutions > Groupe Hospitalier Universitaire Pitié-Salpêtrière (FRANCE)
Other partners > Université Paris Ouest Nanterre La Défense (FRANCE)
Laboratory name:
Deposited On:09 Sep 2016 11:34

Repository Staff Only: item control page