{"id":"https://openalex.org/W4392903630","doi":"https://doi.org/10.1109/icassp48485.2024.10446130","title":"Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers","display_name":"Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903630","doi":"https://doi.org/10.1109/icassp48485.2024.10446130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5103977579","display_name":"Shashi Kumar","orcid":"https://orcid.org/0009-0008-9511-2131"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Shashi Kumar","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021226188","display_name":"Iuliia Nigmatulina","orcid":"https://orcid.org/0000-0002-5111-1873"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iuliia Nigmatulina","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075765823","display_name":"Esa\u00fa Villatoro-Tello","orcid":"https://orcid.org/0000-0002-1322-0358"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Esa\u00fa Villatoro-Tello","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH","CZ"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland","Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114245170","display_name":"Karthik Pandia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099960","display_name":"Systems Control (United States)","ror":"https://ror.org/014tted12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099960"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Pandia","raw_affiliation_strings":["Uniphore Software Systems Inc.,Palo Alto,CA,USA","Uniphore Software Systems Inc., Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems Inc.,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I4210099960"]},{"raw_affiliation_string":"Uniphore Software Systems Inc., Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008235303","display_name":"S. Pavankumar Dubagunta","orcid":"https://orcid.org/0000-0002-4307-8604"},"institutions":[{"id":"https://openalex.org/I4210099960","display_name":"Systems Control (United States)","ror":"https://ror.org/014tted12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099960"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Pavankumar Dubagunta","raw_affiliation_strings":["Uniphore Software Systems Inc.,Palo Alto,CA,USA","Uniphore Software Systems Inc., Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems Inc.,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I4210099960"]},{"raw_affiliation_string":"Uniphore Software Systems Inc., Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083410051","display_name":"Aravind Ganapathiraju","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099960","display_name":"Systems Control (United States)","ror":"https://ror.org/014tted12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099960"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Ganapathiraju","raw_affiliation_strings":["Uniphore Software Systems Inc.,Palo Alto,CA,USA","Uniphore Software Systems Inc., Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems Inc.,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I4210099960"]},{"raw_affiliation_string":"Uniphore Software Systems Inc., Palo Alto, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103977579"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72654048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12592","last_page":"12596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/speech-recognition","display_name":"Speech recognition","score":0.7195262908935547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048901319503784},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6847679615020752},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6697300672531128},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.5488300323486328},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5341576337814331},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5333616137504578},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5282501578330994},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49986815452575684},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.49711325764656067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4418308138847351},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44046714901924133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3461526930332184},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07962512969970703}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195262908935547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048901319503784},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6847679615020752},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6697300672531128},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.5488300323486328},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5341576337814331},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5333616137504578},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5282501578330994},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49986815452575684},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.49711325764656067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4418308138847351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44046714901924133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3461526930332184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07962512969970703},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1489048302","https://openalex.org/W1522301498","https://openalex.org/W1540624770","https://openalex.org/W2111057910","https://openalex.org/W2122364000","https://openalex.org/W2125336414","https://openalex.org/W2168025753","https://openalex.org/W2171700247","https://openalex.org/W2222512263","https://openalex.org/W2509864590","https://openalex.org/W2673722796","https://openalex.org/W2750259098","https://openalex.org/W2808939837","https://openalex.org/W2888867175","https://openalex.org/W2899663614","https://openalex.org/W2933138175","https://openalex.org/W2973127116","https://openalex.org/W3008912312","https://openalex.org/W3013139777","https://openalex.org/W3035390927","https://openalex.org/W3097798370","https://openalex.org/W3160641957","https://openalex.org/W3167895882","https://openalex.org/W3203417382","https://openalex.org/W3212886388","https://openalex.org/W4210811812","https://openalex.org/W4224927243","https://openalex.org/W4287645199","https://openalex.org/W4295312788","https://openalex.org/W4372259861","https://openalex.org/W4372344102","https://openalex.org/W4372346845","https://openalex.org/W4375869109","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6755977528","https://openalex.org/W6766978945","https://openalex.org/W6780226713","https://openalex.org/W6784162623","https://openalex.org/W6796656850"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Traditionally,":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"and":[5,28,83,102,161],"speaker":[6,21,33,114],"change":[7,115],"detection":[8],"(SCD)":[9],"systems":[10],"have":[11],"been":[12,42],"independently":[13],"trained":[14,106],"to":[15,44,55],"generate":[16],"comprehensive":[17],"transcripts":[18],"accompanied":[19],"by":[20,31,134],"turns.":[22],"Recently,":[23],"joint":[24,57],"training":[25,39,58,74],"of":[26,66,79,126,142,151],"ASR":[27,38,92,101,160],"SCD":[29,89,103,137,162],"systems,":[30],"inserting":[32],"turn":[34],"tokens":[35],"in":[36,81,117],"the":[37,56,63,71,97,100,113,118,140,149],"text,":[40],"has":[41],"shown":[43],"be":[45],"successful.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,111],"present":[51],"a":[52,127],"multitask":[53,73,108,159],"alternative":[54],"approach.":[59],"Results":[60,146],"obtained":[61,121],"on":[62,88],"mix-headset":[64],"audios":[65],"AMI":[67],"corpus":[68],"show":[69],"that":[70,148],"proposed":[72],"yields":[75],"an":[76,136],"absolute":[77],"improvement":[78],"1.8%":[80],"coverage":[82],"purity":[84],"based":[85],"F1":[86],"score":[87],"task":[90],"without":[91],"degradation.":[93],"We":[94],"also":[95],"examine":[96],"trade-offs":[98],"between":[99],"performance":[104],"when":[105],"using":[107],"criteria.":[109],"Additionally,":[110],"validate":[112],"information":[116],"embedding":[119,153],"spaces":[120,154],"after":[122],"different":[123,152],"transformer":[124,144],"layers":[125],"self-supervised":[128],"pre-trained":[129],"model,":[130],"such":[131],"as":[132],"XLSR-53,":[133],"integrating":[135],"classifier":[138],"at":[139],"output":[141],"specific":[143],"layers.":[145],"reveal":[147],"use":[150],"from":[155],"XLSR-53":[156],"model":[157],"for":[158],"is":[163],"advantageous.":[164],"<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
