Simulating Dysarthric Speech for Training Data Augmentation in Clinical Speech Applications
Authors:
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6009-6013
Abstract
Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack of access. As a result, clinical speech applications typically rely on small data sets with only tens of speakers. In this paper, we propose a method for simulating training data for clinical applications by transforming healthy speech to dysarthric speech using adversarial training. We evaluate the efficacy of our approach using both objective and subjective criteria. We present the transformed samples to five experienced speech-language pathologists (SLPs) and ask them to identify the samples as healthy or dysarthric. The results reveal that the SLPs identify the transformed speech as dysarthric 65% of the time. In a pilot classification experiment, we show that by using the simulated speech samples to balance an existing dataset, the classification accuracy improves by ~10% after data augmentation.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Convex Weighting Criteria for Speaking Rate EstimationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Automatic intelligibility classification of sentence-level pathological speechComputer Speech & Language, 2015
- The TORGO database of acoustic and articulatory speech from speakers with dysarthriaLanguage Resources and Evaluation, 2011
- Quantifying Speech Rhythm Abnormalities in the DysarthriasJournal of Speech, Language, and Hearing Research, 2009
- Automated Intelligibility Assessment of Pathological Speech Using Phonological FeaturesEURASIP Journal on Advances in Signal Processing, 2009
- Improving the intelligibility of dysarthric speechSpeech Communication, 2007
- Wavelet time-frequency analysis and least squares support vector machines for the identification of voice disordersComputers in Biology and Medicine, 2007
- The Nemours database of dysarthric speech2002
- Automatic speech recognition and a review of its functioning with dysarthric speechAugmentative and Alternative Communication, 2000
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999