@InProceedings{Schubert2024_1224,
author = {Martha Schubert and Yamini Sinha and Julia Krüger and Ingo Siegert},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2024},
title = {Speech Recognition Errors in ASR Engines and Their Impact on Linguistic Analysis in Psychotherapies},
year = {2024},
editor = {Timo Baumann},
month = mar,
pages = {203--210},
publisher = {TUDpress, Dresden},
abstract = {Modern intervention planning in psychotherapies may benefit from predicting process relevant psychotherapy constructs by automated speech analysis. One essential step is the extraction of relevant linguistic speech markers by ASR engines, which because of highly sensible data, work offline. We analyze transcription errors from NeMo, Whisper, and Wav2Vec2.0, focusing on their impact on linguistic markers usually requiring high quality transcripts. By utilizing part-of-speech tagging, we examine error occurrences among different word types. The Linguistic Inquiry and Word Count (LIWC) software aids in extracting markers. We highlight challenges in transcribing spontaneous speech, prevalent in therapy, and compare results with the Mozilla CommonVoice dataset, which features read speech.},
isbn = {978-3-95908-325-6},
issn = {0940-6832},
keywords = {Poster},
url = {https://www.essv.de/pdf/2024_203_210.pdf},
doi = {10.35096/othr/pub-7099},
}