<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3190</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>631</pageFirst>
    <pageLast>635</pageLast>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue>2</issue>
    <volume>15</volume>
    <type>article</type>
    <publisherName>Springer VS</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2023-12-15</completedDate>
    <publishedDate>2023-12-15</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Wie kann videogestütztes Lernen die Erwartungen Studierender und Dozierender erfüllen?</title>
    <abstract language="deu">ZusammenfassungIm BMBF-Verbundprojekt HAnS entwickeln und implementieren neun Hochschulen sowie drei hochschulübergreifende Einrichtungen ein intelligentes Hochschul-Assistenz-System als Open-Source-Lösung. Videobasierte Lehrmaterialien werden verschriftlicht und durch eine Indexierung Stichwortsuchen ermöglicht; geplant ist, über einen KI-Tutor automatisiert Übungsaufgaben zu generieren. Studierende sollen so in ihrem Selbststudium digital unterstützt werden. Die technische Entwicklung wird interdisziplinär – auch sozialwissenschaftlich und pädagogisch – begleitet und in einem iterativen Vorgehen evidenzbasiert entsprechend Design-Based-Research angepasst. Wissen und Wertesystem der Anwender*innen, Didaktik, Ethik, Akzeptanz und Datenschutz werden dabei im Entwicklungsprozess einbezogen.</abstract>
    <parentTitle language="deu">Soziale Passagen</parentTitle>
    <identifier type="issn">1867-0180</identifier>
    <identifier type="doi">10.1007/s12592-023-00478-0</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T00:11:28Z","timestamp":1719015088510},"reference-count":10,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Technische Hochschule N\u00fcrnberg"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soz Passagen"],"published-print":{"date-parts":[[2023,12]]},"abstract":"&lt;jats:title&gt;Zusammenfassung&lt;\/jats:title&gt;&lt;jats:p&gt;Im BMBF-Verbundprojekt HAnS entwickeln und implementieren neun Hochschulen sowie drei hochschul\u00fcbergreifende Einrichtungen ein intelligentes Hochschul-Assistenz-System als Open-Source-L\u00f6sung. Videobasierte Lehrmaterialien werden verschriftlicht und durch eine Indexierung Stichwortsuchen erm\u00f6glicht; geplant ist, \u00fcber einen KI-Tutor automatisiert \u00dcbungsaufgaben zu generieren. Studierende sollen so in ihrem Selbststudium digital unterst\u00fctzt werden. Die technische Entwicklung wird interdisziplin\u00e4r \u2013\u00a0auch sozialwissenschaftlich und p\u00e4dagogisch\u00a0\u2013 begleitet und in einem iterativen Vorgehen evidenzbasiert entsprechend Design-Based-Research angepasst. Wissen und Wertesystem der Anwender*innen, Didaktik, Ethik, Akzeptanz und Datenschutz werden dabei im Entwicklungsprozess einbezogen.&lt;\/jats:p&gt;","DOI":"10.1007\/s12592-023-00478-0","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T08:02:15Z","timestamp":1702627335000},"page":"631-635","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Wie kann videogest\u00fctztes Lernen die Erwartungen Studierender und Dozierender erf\u00fcllen?","How can video-assisted learning fulfil the expectations of students and lecturers?"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-1700-2403","authenticated-orcid":false,"given":"Carolin","family":"Freier","sequence":"first","affiliation":[]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[]},{"given":"Anne-Kathrin","family":"Helten","sequence":"additional","affiliation":[]},{"given":"Franziska","family":"Hoffmann","sequence":"additional","affiliation":[]},{"given":"Marianne","family":"Hunger","sequence":"additional","affiliation":[]},{"given":"L\u00e1szl\u00f3","family":"Kov\u00e1cs","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Richter","sequence":"additional","affiliation":[]},{"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Schmohl","sequence":"additional","affiliation":[]},{"given":"Claudia","family":"Simon","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"478_CR1","volume-title":"Soziale Arbeit im Digitalzeitalter. Eine Profession und ihre Theorien im Kontext digitaler Transformation","author":"A Beranek","year":"2021","unstructured":"Beranek, A. (2021). Soziale Arbeit im Digitalzeitalter. Eine Profession und ihre Theorien im Kontext digitaler Transformation. Weinheim, Basel: Juventa."},{"key":"478_CR2","volume-title":"Das Gruppendiskussionsverfahren in der Forschungspraxis","author":"R Bohnsack","year":"2009","unstructured":"Bohnsack, R., Przyborski, A., &amp; Sch\u00e4ffer, B. (2009). Das Gruppendiskussionsverfahren in der Forschungspraxis. Opladen: Barbara Budrich."},{"key":"478_CR3","doi-asserted-by":"publisher","DOI":"10.36198\/9783838544977","volume-title":"Ethnografie. Die Praxis der Feldforschung","author":"G Breidenstein","year":"2015","unstructured":"Breidenstein, G., Hirschauer, S., Kalthoff, H., &amp; Nieswand, B. (2015). Ethnografie. Die Praxis der Feldforschung. Konstanz: UVK. M\u00fcnchen: UVK\/Lucius. 2. \u00dcberarbeitete Auflage"},{"key":"478_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-658-32556-5","volume-title":"Gegenwart und Zukunft sozialer Dienstleistungsarbeit. Chancen und Risiken der Digitalisierung in der Sozialwirtschaft","author":"C Freier","year":"2021","unstructured":"Freier, C. (2021). Den digitalen Wandel in der Sozialwirtschaft gestalten. In C.\u00a0Freier, J.\u00a0K\u00f6nig, A.\u00a0Manzeschke &amp; B.\u00a0St\u00e4dtler-Mach (Hrsg.), Gegenwart und Zukunft sozialer Dienstleistungsarbeit. Chancen und Risiken der Digitalisierung in der Sozialwirtschaft (S.\u00a01\u201325). Wiesbaden: VS."},{"key":"478_CR5","volume-title":"Handbuch Soziale Arbeit und Digitalisierung","year":"2020","unstructured":"Kutscher, N., Tillmann, A., Zorn, I., Ley, T., Seelmeyer, U., &amp; Siller, F. (Hrsg.). (2020). Handbuch Soziale Arbeit und Digitalisierung (1.\u00a0Aufl.). Weinheim: Beltz Juventa.","edition":"1"},{"key":"478_CR6","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-658-32556-5_6","volume-title":"Gegenwart und Zukunft sozialer Dienstleistungsarbeit. Chancen und Risiken der Digitalisierung in der Sozialwirtschaft","author":"M Nugel","year":"2021","unstructured":"Nugel, M. (2021). Digitalisierung im Studium der Sozialen Arbeit: Bildung in der digitalen Transformation. In C.\u00a0Freier, J.\u00a0K\u00f6nig, A.\u00a0Manzeschke &amp; B.\u00a0St\u00e4dtler-Mach (Hrsg.), Gegenwart und Zukunft sozialer Dienstleistungsarbeit. Chancen und Risiken der Digitalisierung in der Sozialwirtschaft (S.\u00a091\u2013100). Wiesbaden: VS."},{"issue":"10","key":"478_CR7","doi-asserted-by":"publisher","first-page":"368","DOI":"10.5771\/0490-1606-2019-10-368","volume":"68","author":"S Ottmann","year":"2019","unstructured":"Ottmann, S., &amp; K\u00f6nig, J. (2019). Wirkungsanalyse in der Sozialen Arbeit. Differenzierung ist n\u00f6tig. Soziale Arbeit, 68(10), 368\u2013376.","journal-title":"Soziale Arbeit"},{"issue":"2","key":"478_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15460\/eder.4.2.1554","volume":"4","author":"G Reinmann","year":"2020","unstructured":"Reinmann, G. (2020). Ein holistischer Design-Based Research-Modellentwurf f\u00fcr die Hochschuldidaktik. EDeR \u2013 Educational Design Research, 4(2), 1\u201316.","journal-title":"EDeR \u2013 Educational Design Research"},{"key":"478_CR9","first-page":"27","volume-title":"P\u00e4dagogik, Soziale Arbeit und Digitalit\u00e4t. Education, Social Work and Digitality","author":"JK Rennstich","year":"2022","unstructured":"Rennstich, J.\u202fK. (2022). Digitalkompetenz f\u00fcr Soziale Berufe: Der Einfluss der digitalen Informatisierung auf Lehre und Ausbildungsprofile. In J.\u00a0Wahl, I.\u00a0Schell-Kiehl &amp; T.\u00a0Damberger (Hrsg.), P\u00e4dagogik, Soziale Arbeit und Digitalit\u00e4t. Education, Social Work and Digitality (S.\u00a027\u201338). Weinheim: Beltz Verlagsgruppe."},{"key":"478_CR10","doi-asserted-by":"publisher","DOI":"10.36198\/9783838553580","volume-title":"P\u00e4dagogisches Grundwissen f\u00fcr das Studium der Sozialen Arbeit: Ein Kompendium","author":"S Trabandt","year":"2020","unstructured":"Trabandt, S., &amp; Wagner, H.-J. (2020). P\u00e4dagogisches Grundwissen f\u00fcr das Studium der Sozialen Arbeit: Ein Kompendium. Opladen Toronto."}],"container-title":["Soziale Passagen"],"original-title":[],"language":"de","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12592-023-00478-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12592-023-00478-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12592-023-00478-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T12:35:11Z","timestamp":1718973311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12592-023-00478-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":10,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["478"],"URL":"https:\/\/doi.org\/10.1007\/s12592-023-00478-0","relation":{},"ISSN":["1867-0180","1867-0199"],"issn-type":[{"value":"1867-0180","type":"print"},{"value":"1867-0199","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]},"assertion":[{"value":"19 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="local_crossrefLicence">https://creativecommons.org/licenses/by/4.0</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorFirstName_6,PersonAuthorLastName_6,PersonAuthorFirstName_7,PersonAuthorLastName_7,PersonAuthorFirstName_8,PersonAuthorLastName_8,PersonAuthorFirstName_9,PersonAuthorLastName_9,PersonAuthorFirstName_10,PersonAuthorLastName_10,PublisherName,TitleMain_1,Language,TitleAbstract_1,TitleParent_1,PageNumber,PageFirst,PageLast,Issue,Volume,CompletedYear,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Carolin Freier</author>
    <author>Tobias Bocklet</author>
    <author>Anne-Kathrin Helten</author>
    <author>Franziska Hoffmann</author>
    <author>Marianne Hunger</author>
    <author>László Kovács</author>
    <author>Florian Richter</author>
    <author>Korbinian Riedhammer</author>
    <author>Tobias Schmohl</author>
    <author>Claudia Simon</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Hochschulforschung · Intelligente Assistenzsysteme · Evaluation · Video-Lernen · Adressat*innen-zentrierte Technikentwicklung</value>
    </subject>
    <collection role="institutes" number="">Fakultät Sozialwissenschaften</collection>
    <collection role="Forschungsschwerpunkt" number="5">Digitalisierung &amp; Künstliche Intelligenz</collection>
    <collection role="Forschungsschwerpunkt" number="7">Soziale &amp; ökonomische Transformation</collection>
    <collection role="institutes" number="">Zentrum für Künstliche Intelligenz (KIZ)</collection>
  </doc>
  <doc>
    <id>1759</id>
    <completedYear>2020</completedYear>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>42</pageFirst>
    <pageLast>44</pageLast>
    <pageNumber>3</pageNumber>
    <edition/>
    <issue>14</issue>
    <volume>162</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2020-08-13</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Verstehen mich mit der Maske noch alle?</title>
    <title language="eng">Speech quality changes due to face masks</title>
    <abstract language="deu">In Arztpraxen nimmt der Infektionsschutz mittels Mund-Nasen-Maske momentan eine zentrale Rolle ein. Wenig nachgedacht wird dabei über die Folgen für die Kommunikation. Gerade schwerhörigen Patienten bereiten gedämpfte Stimmen und abgedeckte Lippen Probleme.</abstract>
    <parentTitle language="deu">MMW - Fortschritte der Medizin</parentTitle>
    <subTitle language="deu">Coronavirus-Pandemie</subTitle>
    <identifier type="doi">10.1007/s15006-020-0749-4</identifier>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:30:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Maria Schuster</author>
    <author>Tomas Arias-Vergara</author>
    <author>Rainer Müller-Hörner</author>
    <author>Cordula Winterholler</author>
    <author>Tobias Bocklet</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Face mask, speech quality, computer-assisted speech assessment, hearing loss</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1778</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>145-150</pageNumber>
    <edition/>
    <issue>3</issue>
    <volume>47</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2023-09-05</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Künstliche Intelligenz für die Analyse pathologischer Sprache</title>
    <abstract language="deu">Sprache kann eine Vielzahl von diagnostisch relevanten Informationen enthalten. In diesem Übersichtsartikel wird aufgezeigt, wie Methoden der Künstlichen Intelligenz, insbesondere Maschinelles Lernen und Sprachverarbeitung, angewendet auf Sprachsignale eingesetzt werden können: zur Bewertung von Verständlichkeit, zur Automatisierung von standardisierten Tests und zur Bestimmung medizinischer Skalen und Diagnosen. Eine abschließende kritischen Betrachtung von akustischen Merkmalen über eine Vielzahl von Pathologien gibt Grund zur Annahme, dass diese Marker tatsächlich diagnostisch relevante Informationen enthalten.</abstract>
    <abstract language="eng">Speech can contain a variety of diagnostically relevant cues. In this article, it is shown how artificial intelligence, in particular machine learning and speech processing, can be applied to speech signals: to assess intelligibility, to automate standardized tests, and to determine medical scales and diagnoses. We conclude with critical review of acoustic features across a variety of pathologies that give reason to believe that these markers do indeed contain diagnostically relevant information.</abstract>
    <parentTitle language="deu">Sprache - Stimme - Gehör</parentTitle>
    <additionalTitle language="eng">Artificial Intelligence for the Analysis of Pathologic Speech</additionalTitle>
    <identifier type="doi">10.1055/a-2089-5778</identifier>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:38+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Tobias Bocklet</author>
    <author>Elmar Nöth</author>
    <author>Korbinian Riedhammer</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Künstliche Intelligenz - Machine Learning - pathologische Sprache - Spracherkennung - Sprachverarbeitung</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1780</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2023-08-16</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Classifying Dementia in the Presence of Depression</title>
    <abstract language="eng">Automated dementia screening enables early detection and intervention, reducing costs to healthcare systems and increasing quality of life for those affected. Depression has shared symptoms with dementia, adding complexity to diagnoses. The research focus so far has been on binary classification of dementia (DEM) and healthy controls (HC) using speech from picture description tests from a single dataset. In this work, we apply established baseline systems to discriminate cognitive impairment in speech from the semantic Verbal Fluency Test and the Boston Naming Test using text, audio and emotion embeddings in a 3-class classification problem (HC vs. MCI vs. DEM). We perform cross-corpus and mixed-corpus experiments on two independently recorded German datasets to investigate generalization to larger populations and different recording conditions. In a detailed error analysis, we look at depression as a secondary diagnosis to understand what our classifiers actually learn.</abstract>
    <subTitle language="eng">A Cross-Corpus Study</subTitle>
    <identifier type="doi">10.48550/arXiv.2308.08306</identifier>
    <identifier type="arxiv">2308.08306</identifier>
    <enrichment key="ConferenceStatement">Annual Conference of the Int’l Speech Communication Association (INTERSPEECH)</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:39+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Franziska Braun</author>
    <author>Sebastian P. Bayerl</author>
    <author>Paula A. Pérez-Toro</author>
    <author>Florian Hönig</author>
    <author>Hartmut Lehfeld</author>
    <author>Thomas Hillemacher</author>
    <author>Elmar Nöth</author>
    <author>Tobias Bocklet</author>
    <author>Korbinian Riedhammer</author>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1786</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1417</pageFirst>
    <pageLast>1420</pageLast>
    <pageNumber>4</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation>Deutsche Gesellschaft für Akustik</contributingCorporation>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Medical Speech Processing for Diagnosis and Monitoring</title>
    <abstract language="eng">In recent years, speech processing for medical applications got significant traction. While pioneering work in the 1990ies focused on processing sustained vowels or isolated utterances, work in the 2000s already showed, that speech recognition systems, prosodic analysis and natural language processing be used to assess a large variety of speech pathologies.Here, we give an overview of how to classify selected speech pathologies including stuttering, language development, speech intelligibility after surgery, dementia and Alzheimers, depression and state-of-mind. While each of those poses a rather well-defined problem in a lab setting, we discuss the issues when integrating such methods in a clinical workflow such as diagnosis or monitoring. Starting from the question if such detectors can be used for general screening or rather as a specialist's tool, we explore the legal and privacy-related implications: patient-doctor conversations, working with children or demented seniors, bias towards examiner or patient, on-device vs. cloud processing.We conclude with a set of open questions that should be addressed to help bringing all this research from the lab to routine clinical use.</abstract>
    <subTitle language="eng">Clinical Use Cases</subTitle>
    <enrichment key="ConferenceStatement">Fortschritte der Akustik - DAGA 2023</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:43+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Korbinian Riedhammer</author>
    <author>Ilja Baumann</author>
    <author>Sebastian P. Bayerl</author>
    <author>Tobias Bocklet</author>
    <author>Franziska Braun</author>
    <author>Dominik Wagner’</author>
    <collection role="institutes" number="">Zentrum für Künstliche Intelligenz (KIZ)</collection>
  </doc>
  <doc>
    <id>1794</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2318</pageFirst>
    <pageLast>2322</pageLast>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Multi-class Detection of Pathological Speech with Latent Features</title>
    <abstract language="eng">The detection of pathologies from speech features is usually defined as a binary classification task with one class representing a specific pathology and the other class representing healthy speech. In this work, we train neural networks, large margin classifiers, and tree boosting machines to distinguish between four pathologies: Parkinson's disease, laryngeal cancer, cleft lip and palate, and oral squamous cell carcinoma. We show that latent representations extracted at different layers of a pre-trained wav2vec 2.0 system can be effectively used to classify these types of pathological voices. We evaluate the robustness of our classifiers by adding room impulse responses to the test data and by applying them to unseen speech corpora. Our approach achieves unweighted average F1-Scores between 74.1% and 97.0%, depending on the model and the noise conditions used. The systems generalize and perform well on unseen data of healthy speakers sampled from a variety of different sources.</abstract>
    <subTitle language="eng">How does it perform on unseen data?</subTitle>
    <identifier type="doi">10.21437/Interspeech.2023-464</identifier>
    <identifier type="issn">2958-1796</identifier>
    <enrichment key="ConferenceStatement">Annual Conference of the International Speech Communication Association (INTERSPEECH)</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:48+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Dominik Wagner</author>
    <author>Ilja Baumann</author>
    <author>Franziska Braun</author>
    <author>Sebastian P. Bayerl</author>
    <author>Elmar Nöth</author>
    <author>Korbinian Riedhammer</author>
    <author>Tobias Bocklet</author>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1756</id>
    <completedYear>2020</completedYear>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2020-08-27</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Length-and Noise-aware Training Techniques for Short-utterance Speaker Recognition</title>
    <abstract language="eng">Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker recognition systems. The x-vector framework is a popular choice for generating speaker embeddings in recent literature due to its robust training mechanism and excellent performance in various test sets. In this paper, we start with early work on including&#13;
invariant representation learning (IRL) to the loss function and modify the approach with centroid alignment (CA) and length variability cost (LVC) techniques to further improve robustness in noisy, far-field applications. This work mainly focuses on&#13;
improvements for short-duration test utterances (1-8s). We also present improved results on long-duration tasks. In addition, this work discusses a novel self-attention mechanism. On the VOiCES far-field corpus, the combination of the proposed techniques achieves relative improvements of 7.0% for extremely short and 8.2% for full-duration test utterances on equal error rate (EER) over our baseline system.</abstract>
    <identifier type="doi">10.48550/arXiv.2008.12218</identifier>
    <identifier type="arxiv">2008.12218</identifier>
    <enrichment key="ConferenceStatement">Annual Conference of the Int’l Speech Communication Association (INTERSPEECH)</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:30:24+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Wenda Chen</author>
    <author>Jonathan Huang</author>
    <author>Tobias Bocklet</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>speaker recognition, invariant representation learning, centroid alignment, x-vector, far-field</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1795</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>6</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2023-12-07</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Speaker Adaptation for End-To-End Speech Recognition Systems in Noisy Environments</title>
    <abstract language="eng">We analyze the impact of speaker adaptation in end-to-end automatic speech recognition models based on transformers and wav2vec 2.0 under different noise conditions. By including speaker embeddings obtained from x-vector and ECAPA-TDNN systems, as well as i-vectors, we achieve relative word error rate improvements of up to 16.3% on LibriSpeech and up to 14.5% on Switchboard. We show that the proven method of concatenating speaker vectors to the acoustic features and supplying them as auxiliary model inputs remains a viable option to increase the robustness of end-to-end architectures. The effect on transformer models is stronger, when more noise is added to the input speech. The most substantial benefits for systems based on wav2vec 2.0 are achieved under moderate or no noise conditions. Both x-vectors and ECAPA-TDNN embeddings outperform i-vectors as speaker representations. The optimal embedding size depends on the dataset and also varies with the noise condition.</abstract>
    <identifier type="doi">10.48550/arXiv.2211.08774</identifier>
    <identifier type="arxiv">2211.08774</identifier>
    <enrichment key="ConferenceStatement">IEEE Workshop on Speech Recognition and Understanding (ASRU)</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:48+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Dominik Wagner</author>
    <author>Ilja Baumann</author>
    <author>Sebastian P. Bayerl</author>
    <author>Korbinian Riedhammer</author>
    <author>Tobias Bocklet</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speaker adaptation, automatic speech recognition, end-to-end systems, transformer, wav2vec 2.0</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1764</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>150</pageFirst>
    <pageLast>157</pageLast>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>TUDpress, Dresden</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Implementing Easy-to-Use Recipes for the Switchboard Benchmark</title>
    <abstract language="eng">We report on our contribution of templates for tokenization, language modeling, and automatic speech recognition (ASR) on the Switchboard benchmark to the open-source general-purpose toolkit SpeechBrain. Three recipes for the training of end-to-end ASR systems were implemented. We describe their model architectures, as well as the necessary data preparation steps. The word error rates achievable with our models are comparable to or better than those of other popular toolkits. Pre-trained ASR models were made available on HuggingFace. They can be easily integrated into research projects or used directly for quick inference via a hosted inference API.</abstract>
    <enrichment key="ConferenceStatement">Elektronische Sprachsignalverarbeitung 2023</enrichment>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:30:29+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Dominik Wagner</author>
    <author>Sebastian P. Bayerl</author>
    <author>Tobias Bocklet</author>
    <author>Christoph Draxler</author>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1765</id>
    <completedYear>2023</completedYear>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1</pageFirst>
    <pageLast>8</pageLast>
    <pageNumber>8</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Detection of Vowel Errors in Children’s Speech Using Synthetic Phonetic Transcripts</title>
    <abstract language="eng">The analysis of phonological processes is crucial in evaluating speech development disorders in children, but encounters challenges due to limited children audio data. This work focuses on automatic vowel error detection using a two-stage pipeline. The first stage uses a fine-tuned cross-lingual phone recognizer (wav2vec 2.0) to extract phone sequences from audio. The second stage employs a language model (BERT) for classification from a phone sequence, entirely trained on synthetic transcripts, to counteract the very broad range of potential mistakes. We evaluate the system on nonword audio recordings recited by preschool children from a speech development test. The results show that the classifier trained on synthetic data performs well, but its efficacy relies on the quality of the phone recognizer. The best classifier achieves an 94.7% F1 score when evaluated against phonetic ground truths, whereas the F1 score is 76.2% when using automatically recognized phone sequences.</abstract>
    <parentTitle language="eng">2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Taipei, Taiwan, 2023</parentTitle>
    <identifier type="doi">10.1109/ASRU57964.2023.10389704</identifier>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:39:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Ilja Baumann</author>
    <author>Dominik Wagner</author>
    <author>Korbinian Riedhammer</author>
    <author>Elmar Nöth</author>
    <author>Tobias Bocklet</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Conferences ; Pipelines ; Phonetics ; Audio recording ; Speech processing ; Synthetic data ; Automatic speech recognition ; children’s speech ; vowel errors ; nonwords</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1754</id>
    <completedYear>2022</completedYear>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>3643</pageFirst>
    <pageLast>3647</pageLast>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Nonwords Pronunciation Classification in Language Development Tests for Preschool Children</title>
    <abstract language="eng">This work aims to automatically evaluate whether the language development of children is age-appropriate. Validated speech and language tests are used for this purpose to test the auditory memory. In this work, the task is to determine whether spoken nonwords have been uttered correctly. We compare different approaches that are motivated to model specific language structures: Low-level features (FFT), speaker embeddings (ECAPA-TDNN), grapheme-motivated embeddings (wav2vec 2.0), and phonetic embeddings in form of senones (ASR acoustic model). Each of the approaches provides input for VGG-like 5-layer CNN classifiers. We also examine the adaptation per non-word. The evaluation of the proposed systems was performed using recordings from different kindergartens of spoken non- words. ECAPA-TDNN and low-level FFT features do not explicitly model phonetic information; wav2vec2.0 is trained  on grapheme labels, our ASR acoustic model features contain (sub-)phonetic information. We found that the more granular the phonetic modeling is, the higher are the achieved recognition rates. The best system trained on ASR acoustic model features with VTLN achieved an accuracy of 89.4% and an area under the ROC (Receiver Operating Characteristic) curve (AUC) of 0.923. This corresponds to an improvement in accuracy of 20.2% and AUC of 0.309 relative compared to the FFT-baseline</abstract>
    <parentTitle language="eng">Interspeech 2022 : 18-22 September 2022, Incheon, Korea</parentTitle>
    <identifier type="doi">10.21437/Interspeech.2022-10777</identifier>
    <enrichment key="Reviewstatus">Begutachtet/Reviewed</enrichment>
    <enrichment key="opus.import.date">2024-06-27T13:30:21+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">opus_importer</enrichment>
    <licence>Keine Lizenz - Deutsches Urheberrecht gilt</licence>
    <author>Ilja Baumann</author>
    <author>Dominik Wagner</author>
    <author>Sebastian P. Bayerl</author>
    <author>Tobias Bocklet</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>children’s speech, speech assessment, transfer learning</value>
    </subject>
    <collection role="institutes" number="">Fakultät Informatik</collection>
  </doc>
</export-example>
