{"id":"https://openalex.org/W2945165156","doi":"https://doi.org/10.3233/978-1-61499-971-3-81","title":"Evaluation of Deep Clustering for Diarization of Aphasic Speech","display_name":"Evaluation of Deep Clustering for Diarization of Aphasic Speech","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2945165156","doi":"https://doi.org/10.3233/978-1-61499-971-3-81","mag":"2945165156","pmid":"https://pubmed.ncbi.nlm.nih.gov/31118322"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-971-3-81","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-971-3-81","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008746558","display_name":"Daniel Klischies","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Klischies Daniel","raw_affiliation_strings":["Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006648338","display_name":"Christian Kohlschein","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kohlschein Christian","raw_affiliation_strings":["Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834438","display_name":"Cornelius J. Werner","orcid":"https://orcid.org/0000-0002-4624-7995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Werner Cornelius J.","raw_affiliation_strings":["Department of Neurology, Section Interdisciplinary Geriatrics, University Hospital RWTH Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Neurology, Section Interdisciplinary Geriatrics, University Hospital RWTH Aachen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022789731","display_name":"Stephan Jonas","orcid":"https://orcid.org/0000-0002-3687-6165"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Stephan M.","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008746558"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07608963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"260","issue":null,"first_page":"81","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853169441223145},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6844275593757629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6837899684906006},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6327886581420898},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4654211699962616},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.45284900069236755},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42521408200263977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4018230438232422},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3277534246444702},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26627883315086365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853169441223145},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6844275593757629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6837899684906006},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6327886581420898},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4654211699962616},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.45284900069236755},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42521408200263977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018230438232422},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3277534246444702},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26627883315086365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001037","descriptor_name":"Aphasia","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D001037","descriptor_name":"Aphasia","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D001037","descriptor_name":"Aphasia","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D002648","descriptor_name":"Child","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002648","descriptor_name":"Child","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002648","descriptor_name":"Child","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-971-3-81","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-971-3-81","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:31118322","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31118322","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W135211875","https://openalex.org/W1978572805","https://openalex.org/W2052269122","https://openalex.org/W2383807498","https://openalex.org/W4389272081","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W4307477668","https://openalex.org/W2398046462"],"abstract_inverted_index":{"Speaker":[0],"attribution":[1],"and":[2,34,39,60,63,88,125,130,163,196],"labeling":[3],"of":[4,14,48,56,78,80,86,98,142,158,160],"single":[5],"channel,":[6],"multi":[7],"speaker":[8,46,150],"audio":[9,81],"files":[10],"is":[11,64,118,154],"an":[12,105],"area":[13],"active":[15],"research,":[16],"since":[17],"the":[18,54,76,84,123,143,191],"underlying":[19],"problems":[20],"have":[21],"not":[22],"been":[23,179],"solved":[24],"satisfactorily":[25],"yet.":[26],"This":[27,117],"especially":[28],"holds":[29],"true":[30],"for":[31,115],"non-standard":[32],"voices":[33],"speech,":[35],"such":[36,109],"as":[37],"children":[38],"impaired":[40],"speakers.":[41],"Being":[42],"able":[43],"to":[44,147,176,189],"perform":[45],"labelling":[47],"pathological":[49,99],"speech":[50],"would":[51],"potentially":[52],"enable":[53],"development":[55],"computer":[57],"assisted":[58],"diagnosis":[59],"treatment":[61],"systems":[62],"thus":[65],"a":[66,133,149,197],"desirable":[67],"research":[68],"goal.":[69],"In":[70],"this":[71],"manuscript":[72],"we":[73,187],"investigate":[74],"on":[75,96,103,137,156],"applicability":[77],"embeddings":[79],"signals,":[82],"in":[83,182],"form":[85],"time":[87,124,145],"frequency-band":[89],"based":[90],"segments,":[91],"into":[92],"arbitrary":[93],"vector":[94],"spaces":[95],"diarization":[97],"speech.":[100,185],"We":[101,166],"focus":[102],"modifying":[104],"existing":[106],"embedding":[107],"estimator":[108],"that":[110,173],"it":[111],"can":[112],"be":[113],"used":[114],"diarization.":[116],"mainly":[119],"done":[120],"via":[121],"clustering":[122],"frequency":[126,139],"band":[127],"dependant":[128],"vectors":[129,141],"subsequently":[131],"performing":[132],"majority":[134],"vote":[135],"procedure":[136],"all":[138],"dependent":[140],"same":[144],"segment":[146],"assign":[148],"label.":[151],"The":[152],"result":[153],"evaluated":[155],"recordings":[157],"interviews":[159],"aphasia":[161],"patients":[162],"language":[164],"therapists.":[165],"demonstrate":[167],"general":[168],"applicability,":[169],"with":[170,194],"error":[171],"rates":[172],"are":[174],"close":[175],"what":[177],"has":[178],"previously":[180],"achieved":[181],"diarizing":[183],"children's":[184],"Additionally,":[186],"propose":[188],"enhance":[190],"processing":[192],"pipelines":[193],"smoothing":[195],"more":[198],"sophisticated,":[199],"energy":[200],"based,":[201],"voting":[202],"scheme.":[203]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
