The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification

TL;DR

This study investigates how speech recognition errors affect dementia classification, revealing that higher error rates in ASR can sometimes improve classification accuracy in clinical speech analysis.

Contribution

It demonstrates that imperfect ASR transcripts can outperform verbatim transcripts for dementia detection, challenging assumptions about the necessity of high transcription accuracy.

Findings

Higher error rate ASR transcripts can improve classification accuracy.

Imperfect transcripts may contain more relevant linguistic cues.

ASR performance varies with clinical speech complexity.

Abstract

Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment. The feasibility of deploying automated tools that can classify language samples obtained from speech in large-scale clinical settings depends on the ability to capture and automatically transcribe the speech for subsequent analysis. However, the impressive performance of self-supervised learning (SSL) automatic speech recognition (ASR) models with curated speech data is not apparent with challenging speech samples from clinical settings. One of the key questions for successfully applying ASR models for clinical applications is whether imperfect transcripts they generate provide sufficient information for downstream tasks to operate at an acceptable level of accuracy. In this study, we examine the relationship between the errors produced by several deep learning ASR systems and their impact on the downstream task of dementia classification. One of our key findings is that, paradoxically, ASR systems with relatively high error rates can produce transcripts that result in better downstream classification accuracy than classification based on verbatim transcripts.