<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>8051</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress</publisherName>
    <publisherPlace>Dresden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-04-27</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Cross lingual transfer learning does not improve aphasic speech recognition</title>
    <abstract language="eng">In addressing the particular linguistic challenges posed by patients suffering from aphasia, a language disorder, this paper proposes a fine-tuning approach to enhance the speech recognition capabilities of existing models. The available aphasic research data in German is highly limited. To address this constraint, we propose a cross-lingual transfer approach to utilize English data to improve performance in German. This advancement aims to support the development of a therapy platform tailored for patients with aphasia. For the base speech recognition model, we choose to use OpenAI’s Whisper model, and for fine-tuning, we make use of TalkBank’s AphasiaBank. The experimental findings demonstrate that the transcription of aphasic audio with Whisper is less successful than non-aphasic audio. However, fine-tuning the transcription in the respective language resulted in an enhancement of its quality. In contrast, fine-tuning the transcription in another language and expecting a transfer of the learned aphasic speech properties led to a deterioration in its quality.</abstract>
    <parentTitle language="eng">Elektronische Sprachsignalverarbeitung 2025: Tagungsband der 36. Konferenz Halle/Saale, 05.–07. MÄRZ 2025</parentTitle>
    <identifier type="url">https://www.essv.de/pdf/2025_77_84.pdf</identifier>
    <identifier type="isbn">978-3-95908-803-9</identifier>
    <identifier type="issn">0940-6832</identifier>
    <identifier type="urn">urn:nbn:de:bvb:898-opus4-80518</identifier>
    <identifier type="doi">10.35096/othr/pub-8051</identifier>
    <enrichment key="OtherSeries">Studientexte zur Sprachkommunikation, 110</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Sara Mühlhausen</author>
    <author>Sarah Gomez</author>
    <author>Norina Lauer</author>
    <author>Timo Baumann</author>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Automatische Spracherkennung</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Sprachdialogsystem</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Aphasie</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="institutes" number="FakSoz">Fakultät Sozial- und Gesundheitswissenschaften</collection>
    <collection role="persons" number="lauerlp">Lauer, Norina (Prof. Dr.) - Labor Logopädie</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
    <collection role="DFGFachsystematik" number="1">Ingenieurwissenschaften</collection>
    <thesisPublisher>Ostbayerische Technische Hochschule Regensburg</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-oth-regensburg/files/8051/2025_77_84.pdf</file>
  </doc>
</export-example>
