EasyCall corpus: a dysarthric speech dataset

TL;DR

The EasyCall corpus is a comprehensive Italian dysarthric speech dataset designed to aid the development of speech recognition assistive technologies, highlighting current system limitations and providing a valuable resource for future research.

Contribution

This paper introduces the largest and most detailed dysarthric speech dataset to date, including diverse commands and non-commands for improved ASR system training.

Findings

Commercial ASR systems perform poorly on the dataset

The corpus includes 21,386 recordings from 55 speakers

The dataset supports development of voice-controlled assistive apps

Abstract

This paper introduces a new dysarthric speech command dataset in Italian, called EasyCall corpus. The dataset consists of 21386 audio recordings from 24 healthy and 31 dysarthric speakers, whose individual degree of speech impairment was assessed by neurologists through the Therapy Outcome Measure. The corpus aims at providing a resource for the development of ASR-based assistive technologies for patients with dysarthria. In particular, it may be exploited to develop a voice-controlled contact application for commercial smartphones, aiming at improving dysarthric patients' ability to communicate with their family and caregivers. Before recording the dataset, participants were administered a survey to evaluate which commands are more likely to be employed by dysarthric individuals in a voice-controlled contact application. In addition, the dataset includes a list of non-commands (i.e., words near/inside commands or phonetically close to commands) that can be leveraged to build a more robust command recognition system. At present commercial ASR systems perform poorly on the EasyCall Corpus as we report in this paper. This result corroborates the need for dysarthric speech corpora for developing effective assistive technologies. To the best of our knowledge, this database represents the richest corpus of dysarthric speech to date.