{"id":"https://openalex.org/W3154262773","doi":"https://doi.org/10.21437/interspeech.2019-1126","title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","display_name":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W3154262773","doi":"https://doi.org/10.21437/interspeech.2019-1126","mag":"3154262773"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"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/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"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/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5149,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.92630683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9922999739646912,"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":0.800346314907074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7161995768547058},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5613009929656982},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5451686382293701},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5244032144546509},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4350753128528595},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.42430785298347473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3502025902271271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30850836634635925},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09333887696266174}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.800346314907074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7161995768547058},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5613009929656982},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5451686382293701},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5244032144546509},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4350753128528595},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.42430785298347473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3502025902271271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30850836634635925},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09333887696266174},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","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/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0,155],"this":[1,147],"paper,":[2],"we":[3,161],"propose":[4],"a":[5,26,34,63,92,108,120,128,151,178],"novel":[6],"auxiliary":[7,43,166],"loss":[8,44,138,172],"function":[9,45],"for":[10,66,169,177,181],"target-speaker":[11,75,94],"automatic":[12],"speech":[13,32,84],"recognition":[14],"(ASR).":[15],"Our":[16],"method":[17,81],"automatically":[18],"extracts":[19],"and":[20],"transcribes":[21],"target":[22,39],"speaker's":[23],"utterances":[24],"from":[25],"monaural":[27],"mixture":[28],"of":[29,37,113,133,153],"multiple":[30],"speakers":[31],"given":[33],"short":[35],"sample":[36],"the":[38,59,74,99,116,141,158,165,170],"speaker.":[40],"The":[41],"proposed":[42,80,137,171],"attempts":[46],"to":[47,61,146,157],"additionally":[48],"maximize":[49],"interference":[50,182],"speaker":[51,67],"ASR":[52,95,122,180],"accuracy":[53,72,159],"during":[54],"training.":[55],"This":[56,105],"will":[57],"regularize":[58],"network":[60],"achieve":[62],"better":[64,71],"representation":[65],"separation,":[68],"thus":[69],"achieving":[70,150],"on":[73,98,115],"ASR.":[76],"We":[77,89],"evaluated":[78],"our":[79,136],"using":[82],"two-speaker-mixed":[83],"in":[85],"various":[86],"signal-to-interference-ratio":[87],"conditions.":[88],"first":[90],"built":[91],"strong":[93,148],"baseline":[96,106],"based":[97],"state-of-the-art":[100],"lattice-free":[101],"maximum":[102],"mutual":[103],"information.":[104],"achieved":[107],"word":[109],"error":[110],"rate":[111],"(WER)":[112],"18.06%":[114],"test":[117],"set":[118],"while":[119],"normal":[121],"trained":[123],"with":[124],"clean":[125],"data":[126],"produced":[127],"completely":[129],"corrupted":[130],"result":[131],"(WER":[132],"84.71%).":[134],"Then,":[135],"further":[139],"reduced":[140],"WER":[142,152],"by":[143],"6.6%":[144],"relative":[145],"baseline,":[149],"16.87%.":[154],"addition":[156],"improvement,":[160],"also":[162],"showed":[163],"that":[164],"output":[167],"branch":[168],"can":[173],"even":[174],"be":[175],"used":[176],"secondary":[179],"speakers'":[183],"speech.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}