ASHA journals
Browse
IMAGE
S1_JSLHR-24-00049tetzloff.png (5.71 kB)
DOCUMENT
S2_JSLHR-24-00049tetzloff.pdf (491.58 kB)
IMAGE
S3_JSLHR-24-00049tetzloff.png (6.7 kB)
1/0
3 files

ASR in PPAOS (Tetzloff et al., 2024)

Download all (504 kB)
online resource
posted on 2024-08-06, 17:05 authored by Katerina A. Tetzloff, Daniela Wiepert, Hugo Botha, Joseph R. Duffy, Heather M. Clark, Jennifer L. Whitwell, Keith A. Josephs, Rene L. Utianski

Introduction: Transcribing disordered speech can be useful when diagnosing motor speech disorders such as primary progressive apraxia of speech (PPAOS), who have sound additions, deletions, and substitutions, or distortions and/or slow, segmented speech. Since transcribing speech can be a laborious process and requires an experienced listener, using automatic speech recognition (ASR) systems for diagnosis and treatment monitoring is appealing. This study evaluated the efficacy of a readily available ASR system (wav2vec 2.0) in transcribing speech of PPAOS patients to determine if the word error rate (WER) output by the ASR can differentiate between healthy speech and PPAOS and/or among its subtypes, whether WER correlates with AOS severity, and how the ASR’s errors compare to those noted in manual transcriptions.

Method: Forty-five patients with PPAOS and 22 healthy controls were recorded repeating 13 words, 3 times each, which were transcribed manually and using wav2vec 2.0. The WER and phonetic and prosodic speech errors were compared between groups, and ASR results were compared against manual transcriptions.

Results: Mean overall WER was 0.88 for patients and 0.33 for controls. WER significantly correlated with AOS severity and accurately distinguished between patients and controls but not between AOS subtypes. The phonetic and prosodic errors from the ASR transcriptions were also unable to distinguish between subtypes, whereas errors calculated from human transcriptions were. There was poor agreement in the number of phonetic and prosodic errors between the ASR and human transcriptions.

Conclusions: This study demonstrates that ASR can be useful in differentiating healthy from disordered speech and evaluating PPAOS severity but does not distinguish PPAOS subtypes. ASR transcriptions showed weak agreement with human transcriptions; thus, ASR may be a useful tool for the transcription of speech in PPAOS, but the research questions posed must be carefully considered within the context of its limitations.

Supplemental Material S1. Apraxia of Speech Rating Scale by word error rate.

Supplemental Material S2. Demographics of participants included in error analysis.

Supplemental Material S3. Percentage of words with an error (manual) by word error rate (automatic speech recognition).

Tetzloff, K. A., Wiepert, D., Botha, H., Duffy, J. R., Clark, H. M., Whitwell, J. L., Josephs, K. A., & Utianski, R. L. (2024). Automatic speech recognition in primary progressive apraxia of speech. Journal of Speech, Language, and Hearing Research, 67(9), 2964–2976. https://doi.org/10.1044/2024_JSLHR-24-00049

Funding

This work was supported by the National Institutes of Health Grants R01 AG 83832 (PI: Botha), R01-DC12519 (PI: Whitwell), R01-DC14942 (PI: Utianski/Josephs), and R01-DC010367 (PI: Josephs). The funder had no role in the design, data collection, data analysis, and reporting of this study.

History