{"id":"https://openalex.org/W3007946293","doi":"https://doi.org/10.1109/asru46091.2019.9004009","title":"Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models","display_name":"Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007946293","doi":"https://doi.org/10.1109/asru46091.2019.9004009","mag":"3007946293"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004009","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101012633","display_name":"Yawen Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yawen Xue","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6152,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94518167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"38"},"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":0.9995999932289124,"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":0.9987999796867371,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9135783910751343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8190751075744629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786377668380737},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6659462451934814},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5915538668632507},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5759257674217224},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5561968684196472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38862165808677673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3668637275695801}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9135783910751343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8190751075744629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786377668380737},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6659462451934814},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5915538668632507},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5759257674217224},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5561968684196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38862165808677673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3668637275695801}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004009","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":60,"referenced_works":["https://openalex.org/W87954838","https://openalex.org/W262275730","https://openalex.org/W1524333225","https://openalex.org/W1876378865","https://openalex.org/W1965819578","https://openalex.org/W1989674786","https://openalex.org/W2025917366","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2093499222","https://openalex.org/W2099621636","https://openalex.org/W2117671523","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2221409856","https://openalex.org/W2395106899","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2460742184","https://openalex.org/W2514741789","https://openalex.org/W2558649592","https://openalex.org/W2569324142","https://openalex.org/W2620757702","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2749475572","https://openalex.org/W2749510669","https://openalex.org/W2787290364","https://openalex.org/W2787692317","https://openalex.org/W2888909726","https://openalex.org/W2889418727","https://openalex.org/W2889503488","https://openalex.org/W2890244912","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2900440209","https://openalex.org/W2937170468","https://openalex.org/W2962788625","https://openalex.org/W2963164596","https://openalex.org/W2963470929","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3034729383","https://openalex.org/W3099832538","https://openalex.org/W3154262773","https://openalex.org/W6603550504","https://openalex.org/W6609683914","https://openalex.org/W6631362777","https://openalex.org/W6647485478","https://openalex.org/W6674036243","https://openalex.org/W6675409298","https://openalex.org/W6712930963","https://openalex.org/W6713762819","https://openalex.org/W6738902873","https://openalex.org/W6766883552","https://openalex.org/W6779469704","https://openalex.org/W6785623113"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,32,58,61,71,90,100,109,120,130,136,190],"use":[4],"of":[5,18,34,43,49,70,76,92,166,189],"target-speaker":[6],"automatic":[7],"speech":[8,13,33],"recognition":[9,14],"(TS-ASR)":[10],"for":[11],"simultaneous":[12],"and":[15,29,95,141,183],"speaker":[16,37,93,102,121,152,170,177,193],"diarization":[17,142,178,194],"single-channel":[19],"dialogue":[20,116],"recordings.":[21],"TS-ASR":[22,50,97,167],"is":[23,51],"a":[24,35,39,68,156,181],"technique":[25],"to":[26],"automatically":[27],"extract":[28],"recognize":[30],"only":[31,161],"target":[36,72],"given":[38,168],"short":[40],"sample":[41,69],"utterance":[42],"that":[44,52,129,158,165,188],"speaker.":[45],"One":[46],"obvious":[47],"drawback":[48],"it":[53,66],"cannot":[54],"be":[55],"used":[56],"when":[57],"speakers":[59,73],"in":[60,74,87,118],"recordings":[62,117],"are":[63,104],"unknown":[64],"because":[65],"requires":[67],"advance":[75],"decoding.":[77],"To":[78],"remove":[79],"this":[80],"limitation,":[81],"we":[82],"propose":[83],"an":[84],"iterative":[85],"method,":[86],"which":[88,119],"(i)":[89],"estimation":[91],"embeddings":[94,103,153],"(ii)":[96],"based":[98,196],"on":[99,197],"estimated":[101],"alternately":[105],"executed.":[106],"We":[107,127],"evaluated":[108],"proposed":[110,131,147],"method":[111,132,148,174,195],"by":[112,160],"using":[113],"very":[114],"challenging":[115],"overlap":[122],"ratio":[123],"was":[124],"over":[125],"20%.":[126],"confirmed":[128],"significantly":[133],"reduced":[134],"both":[135],"word":[137],"error":[138,143],"rate":[139,144],"(WER)":[140],"(DER).":[145],"Our":[146],"combined":[149],"with":[150],"i-vector":[151],"ultimately":[154],"achieved":[155,184],"WER":[157],"differed":[159],"2.1":[162],"%":[163],"from":[164],"oracle":[169],"embeddings.":[171],"Furthermore,":[172],"our":[173],"can":[175],"solve":[176],"simultaneously":[179],"as":[180],"by-product":[182],"better":[185],"DER":[186],"than":[187],"conventional":[191],"clustering-based":[192],"i-vector.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}