Speech analysis and training methods for atypical speech

  • Research type

    Research Study

  • Full title

    Speech analysis and training methods for atypical speech

  • IRAS ID

    319049

  • Contact name

    Stefan Goetze

  • Contact email

    s.goetze@sheffield.ac.uk

  • Sponsor organisation

    University of Sheffield

  • Duration of Study in the UK

    3 years, 2 months, 1 days

  • Research summary

    Dysarthria is a type of motor disorder that reflects abnormalities in the motor movements required for speech production. Speech technologies have a fundamental role in the clinical management of speech disorders. Automatic speech recognition (ASR) (i.e. the task of transforming audio data to text transcriptions) has important implications for assistive communication devices and home environment systems. Alternative and Augmentative Communication (AAC) is defined as a range of techniques that support or replace spoken communication.The Royal College of Speech and Language Therapists (RCSLT) outline the use of AAC devices in the treatment of dysarthria, and AAC devices have become standard practice in clinical intervention. Although the accuracy of ASR systems for typical speech have improved significantly, there are challenges that have limited dysarthric ASR system development and the generalisation of typical speech ASR systems to dysarthric speech. Accordingly, studies have focused on i) adapting typical speech ASR models with dysarthric speech data and ii) collecting further dysarthric data (although the volume and range of dysarthric data remains limited). Furthermore, the classification of dysarthria, including measures of speech intelligibility are important metrics for the management of dysarthria, including assessment of the severity of dysarthria and functional communication. In current practice, metrics are based on subjective listening evaluation by expert human listeners which require high human effort and cost. Recent studies have implemented automated methods to classify dysarthric speech, including automatic estimators of speech intelligibility.

    To advance the application of speech technologies to the clinical management of atypical speech, the current project aims to 1) collect a corpus of dysarthric data to increase the volume of quality dysarthric data available to the research community, 2) improve the performance of dysarthric ASR systems, including methods of model adaptation, and 3) create automated estimators for the classification of dysarthria.

  • REC name

    London - Camberwell St Giles Research Ethics Committee

  • REC reference

    24/LO/0198

  • Date of REC Opinion

    12 Apr 2024

  • REC opinion

    Further Information Favourable Opinion