Speech Intelligibility Classifiers from 550k Disordered Speech Samples

Autor:	Venugopalan, Subhashini, Tobin, Jimmy, Yang, Samuel J., Seaver, Katie, Cave, Richard J. N., Jiang, Pan-Pan, Zeghidour, Neil, Heywood, Rus, Green, Jordan, Brenner, Michael P.
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	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). Comment: ICASSP 2023 camera-ready
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.07533 Zobrazit plný text záznamu View this record from Arxiv