Simulating dysarthric speech for training data augmentation in clinical speech applications

TL;DR

This paper introduces a method to generate dysarthric speech from healthy speech using adversarial training, aiming to augment training data for clinical speech applications where data scarcity is a challenge.

Contribution

It presents a novel adversarial training approach to simulate dysarthric speech, improving data availability for clinical speech machine learning models.

Findings

SLPs identified transformed speech as dysarthric 65% of the time

Data augmentation increased classification accuracy by about 10%

The approach is validated through objective and subjective evaluations

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 are typically developed using 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 about 10% after data augmentation.