Enhancing Voice Wake-Up for Dysarthria: Mandarin Dysarthria Speech Corpus Release and Customized System Design

TL;DR

This paper introduces a new Mandarin dysarthria speech dataset and a specialized wake-up word spotting system to improve voice-controlled smart home devices for individuals with speech impairments.

Contribution

It releases the first open-source Mandarin dysarthria speech corpus and develops a robust customized wake-up system tailored for dysarthric speech.

Findings

The dataset includes diverse demographic and disease information.

The customized system demonstrates high robustness and performance.

Challenges of dysarthric speech variability are highlighted.

Abstract

Smart home technology has gained widespread adoption, facilitating effortless control of devices through voice commands. However, individuals with dysarthria, a motor speech disorder, face challenges due to the variability of their speech. This paper addresses the wake-up word spotting (WWS) task for dysarthric individuals, aiming to integrate them into real-world applications. To support this, we release the open-source Mandarin Dysarthria Speech Corpus (MDSC), a dataset designed for dysarthric individuals in home environments. MDSC encompasses information on age, gender, disease types, and intelligibility evaluations. Furthermore, we perform comprehensive experimental analysis on MDSC, highlighting the challenges encountered. We also develop a customized dysarthria WWS system that showcases robustness in handling intelligibility and achieving exceptional performance. MDSC will be released on https://www.aishelltech.com/AISHELL_6B.