<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>7099</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>203</pageFirst>
    <pageLast>210</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Speech Recognition Errors in ASR Engines and Their Impact on Linguistic Analysis in Psychotherapies</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="deu">Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. März 2024</parentTitle>
    <identifier type="isbn">978-3-95908-325-6</identifier>
    <identifier type="doi">10.35096/othr/pub-7099</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-70999</identifier>
    <enrichment key="OtherSeries">Studientexte zur Sprachkommunikation ; 107</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Martha Schubert</author>
    <author>Yamini Sinha</author>
    <author>Julia Krüger</author>
    <author>Ingo Siegert</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/7099/essv2024_203.pdf</file>
  </doc>
</export-example>
