Alert button
Picture for Richard J. N. Cave

Richard J. N. Cave

Alert button

Speech Intelligibility Classifiers from 550k Disordered Speech Samples

Mar 15, 2023
Subhashini Venugopalan, Jimmy Tobin, Samuel J. Yang, Katie Seaver, Richard J. N. Cave, Pan-Pan Jiang, Neil Zeghidour, Rus Heywood, Jordan Green, Michael P. Brenner

Figure 1 for Speech Intelligibility Classifiers from 550k Disordered Speech Samples
Figure 2 for Speech Intelligibility Classifiers from 550k Disordered Speech Samples
Figure 3 for Speech Intelligibility Classifiers from 550k Disordered Speech Samples
Figure 4 for Speech Intelligibility Classifiers from 550k Disordered Speech Samples

We developed dysarthric speech intelligibility classifiers on 551,176 disordered speech samples contributed by a diverse set of 468 speakers, with a range of self-reported speaking disorders and rated for their overall intelligibility on a five-point scale. We trained three models following different deep learning approaches and evaluated them on ~94K utterances from 100 speakers. We further found the models to generalize well (without further training) on the TORGO database (100% accuracy), UASpeech (0.93 correlation), ALS-TDI PMP (0.81 AUC) datasets as well as on a dataset of realistic unprompted speech we gathered (106 dysarthric and 76 control speakers,~2300 samples).

* ICASSP 2023 camera-ready 
Viaarxiv icon