An analysis of degenerating speech due to progressive dysarthria on ASR performance

TL;DR

This study examines how ASR performance declines over time in individuals with degenerating speech due to ALS and highlights the importance of continuous model updating for maintaining recognition accuracy.

Contribution

It provides a longitudinal analysis of ASR degradation in degenerative speech and demonstrates the effectiveness of ongoing model retraining with new data.

Findings

All models' performance degraded over time as speech impairment increased.

Personalized A-SD models improved significantly with updates from severe speech stages.

Early recordings before speech degradation did not enhance model performance.

Abstract

Although personalized automatic speech recognition (ASR) models have recently been designed to recognize even severely impaired speech, model performance may degrade over time for persons with degenerating speech. The aims of this study were to (1) analyze the change of performance of ASR over time in individuals with degrading speech, and (2) explore mitigation strategies to optimize recognition throughout disease progression. Speech was recorded by four individuals with degrading speech due to amyotrophic lateral sclerosis (ALS). Word error rates (WER) across recording sessions were computed for three ASR models: Unadapted Speaker Independent (U-SI), Adapted Speaker Independent (A-SI), and Adapted Speaker Dependent (A-SD or personalized). The performance of all three models degraded significantly over time as speech became more impaired, but the performance of the A-SD model improved markedly when it was updated with recordings from the severe stages of speech progression. Recording additional utterances early in the disease before speech degraded significantly did not improve the performance of A-SD models. Overall, our findings emphasize the importance of continuous recording (and model retraining) when providing personalized models for individuals with progressive speech impairments.