{"id":"https://openalex.org/W3097643313","doi":"https://doi.org/10.21437/interspeech.2020-1085","title":"Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of any Number of Speakers","display_name":"Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of any Number of Speakers","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097643313","doi":"https://doi.org/10.21437/interspeech.2020-1085","mag":"3097643313"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1085","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345062","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0001-9991-6892"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103218426","display_name":"Tianyan Zhou","orcid":"https://orcid.org/0000-0003-3238-2982"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tianyan Zhou","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corp","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101618071"],"corresponding_institution_ids":["https://openalex.org/I4210105678"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976000189781189,"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":0.9825999736785889,"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":0.7755126953125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.752455472946167},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7452133893966675},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6609323024749756},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6603171825408936},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5769523978233337},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4836317300796509},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4713166356086731},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.468152791261673},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05977964401245117}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755126953125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.752455472946167},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7452133893966675},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6609323024749756},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6603171825408936},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5769523978233337},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4836317300796509},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4713166356086731},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.468152791261673},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05977964401245117},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1085","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1876378865","https://openalex.org/W1989674786","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2133564696","https://openalex.org/W2221409856","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2936774411","https://openalex.org/W2939690918","https://openalex.org/W2952752702","https://openalex.org/W2963477857","https://openalex.org/W2963574857","https://openalex.org/W2963773971","https://openalex.org/W2963979492","https://openalex.org/W2973127116","https://openalex.org/W2973730722","https://openalex.org/W2999547272","https://openalex.org/W3000358149","https://openalex.org/W3008283340","https://openalex.org/W3008762051","https://openalex.org/W3016244460","https://openalex.org/W3095189764","https://openalex.org/W3154262773","https://openalex.org/W4288083483","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,42,55],"end-to-end":[3],"speaker-attributed":[4,72,100],"automatic":[5],"speech":[6,13,40,84,111],"recognition":[7,85,112],"model":[8,22,67],"that":[9,93,107],"unifies":[10],"speaker":[11,16,52,60,87,114],"counting,":[12],"recognition,":[14],"and":[15,86,113],"identification":[17],"on":[18,25,89],"monaural":[19],"overlapped":[20,39,83,110],"speech.Our":[21],"is":[23],"built":[24],"serialized":[26],"output":[27],"training":[28],"(SOT)":[29],"with":[30],"attention-based":[31],"encoder-decoder,":[32],"a":[33,51,79],"recently":[34],"proposed":[35,95],"method":[36,96],"for":[37,82],"recognizing":[38],"comprising":[41],"arbitrary":[43],"number":[44],"of":[45],"speakers.We":[46],"extend":[47],"SOT":[48],"by":[49,71],"introducing":[50],"inventory":[53],"as":[54,62,64],"auxiliary":[56],"input":[57],"to":[58],"produce":[59],"labels":[61],"well":[63],"multi-speaker":[65],"transcriptions.All":[66],"parameters":[68],"are":[69],"optimized":[70],"maximum":[73],"mutual":[74],"information":[75],"criterion,":[76],"which":[77],"represents":[78],"joint":[80],"probability":[81],"identification.Experiments":[88],"LibriSpeech":[90],"corpus":[91],"show":[92],"our":[94],"achieves":[97],"significantly":[98],"better":[99],"word":[101],"error":[102],"rate":[103],"than":[104],"the":[105],"baseline":[106],"separately":[108],"performs":[109],"identification.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
