Tools and technologies for computer-aided speech and language therapy

Saz, Oscar; Yin, Shou-Chun; Lleida, Eduardo; Rose, Richard; Vaquero, Carlos; Rodríguez-Dueñas, William R.

doi:https://doi.org/10.1016/j.specom.2009.04.006

Ítem

Solo Metadatos

Tools and technologies for computer-aided speech and language therapy

https://repository.urosario.edu.co/handle/10336/27120
https://doi.org/10.1016/j.specom.2009.04.006

Autores

Saz, Oscar

Yin, Shou-Chun

Lleida, Eduardo

Rose, Richard

Vaquero, Carlos

Rodríguez-Dueñas, William R.

Fecha

2009-10

Editor

Elsevier

Buscar en:

Métricas alternativas

Abstract

This paper addresses the problem of Computer-Aided Speech and Language Therapy (CASLT). The goal of the work described in the paper is to develop and evaluate a semi-automated system for providing interactive speech therapy to the increasing population of impaired individuals and help professional speech therapists. A discussion on the development and evaluation of a set of interactive therapy tools, along with the underlying speech technologies that support these tools is provided. The interactive tools are designed to facilitate the acquisition of language skills in the areas of basic phonatory skills, phonetic articulation and language understanding primarily for children with neuromuscular disorders like dysarthria. Human–machine interaction for all of these areas requires the existence of speech analysis, speech recognition, and speech verification algorithms that are robust with respect to the sources of speech variability that are characteristic of this population of speakers. The paper will present an experimental study that demonstrates the effectiveness of an interactive system for eliciting speech from a population of impaired children and young speakers ranging in age from 11 to 21 years. The performance of automatic speech recognition (ASR) systems and subword-based pronunciation verification (PV) on this domain are also presented. The results indicate that ASR and PV systems configured from speech utterances taken from the impaired speech domain can provide adequate performance, similar to the experts’ agreement rate, for supporting the presented CASLT applications.