{"id":"https://openalex.org/W4372259861","doi":"https://doi.org/10.1109/icassp49357.2023.10094955","title":"Augmenting Transformer-Transducer Based Speaker Change Detection with Token-Level Training Loss","display_name":"Augmenting Transformer-Transducer Based Speaker Change Detection with Token-Level Training Loss","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259861","doi":"https://doi.org/10.1109/icassp49357.2023.10094955"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5078020198","display_name":"Guanlong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanlong Zhao","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108047863","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-5483-0243"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053487978","display_name":"Yiling Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiling Huang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez Moreno","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4684,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85260624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937000274658203,"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":0.9889000058174133,"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/security-token","display_name":"Security token","score":0.9123460054397583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7550389766693115},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6706678867340088},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6546105742454529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5888452529907227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41804203391075134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40683066844940186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12733247876167297},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06970900297164917},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06666526198387146}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9123460054397583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550389766693115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6706678867340088},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6546105742454529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5888452529907227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41804203391075134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40683066844940186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12733247876167297},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06970900297164917},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06666526198387146},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1482605500","https://openalex.org/W1579838312","https://openalex.org/W1591607137","https://openalex.org/W1828163288","https://openalex.org/W1876378865","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2131342762","https://openalex.org/W2150769028","https://openalex.org/W2171700247","https://openalex.org/W2589330059","https://openalex.org/W2606722458","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2750259098","https://openalex.org/W2889203268","https://openalex.org/W2890964092","https://openalex.org/W2962765220","https://openalex.org/W2962788625","https://openalex.org/W2973127116","https://openalex.org/W3015678936","https://openalex.org/W3016010032","https://openalex.org/W3109950060","https://openalex.org/W3147994063","https://openalex.org/W3203417382","https://openalex.org/W3208240190","https://openalex.org/W4307415927","https://openalex.org/W6603931906","https://openalex.org/W6628911050","https://openalex.org/W6638749077","https://openalex.org/W6639431793","https://openalex.org/W6802591457","https://openalex.org/W6846909052"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W3016124757","https://openalex.org/W4309128991","https://openalex.org/W4372259861"],"abstract_inverted_index":{"In":[0],"this":[1,58],"work":[2],"we":[3,60],"propose":[4,105],"a":[5,62,87,106,120],"novel":[6],"token-based":[7],"training":[8,42,80,130],"strategy":[9],"that":[10,111,127],"improves":[11],"Transformer-Transducer":[12],"(T-T)":[13],"based":[14,23,47],"speaker":[15,38,101],"change":[16],"detection":[17,54],"(SCD)":[18],"performance.":[19],"The":[20],"conventional":[21,45],"T-T":[22,46],"SCD":[24,48,70,140],"model":[25,49,83,97,141],"loss":[26,50],"optimizes":[27],"all":[28],"output":[29],"tokens":[30],"equally.":[31],"Due":[32],"to":[33,52,66,85],"the":[34,37,41,44,68,91,96,128,135,139,143],"sparsity":[35],"of":[36,90,108,122,138,146],"changes":[39],"in":[40],"data,":[43],"leads":[51],"sub-optimal":[53],"accuracy.":[55],"To":[56],"mitigate":[57],"issue,":[59],"use":[61,116],"customized":[63],"edit-distance":[64],"algorithm":[65],"estimate":[67],"token-level":[69],"false":[71,75],"accept":[72],"(FA)":[73],"and":[74,81,93],"reject":[76],"(FR)":[77],"rates":[78],"during":[79],"optimize":[82],"parameters":[84],"minimize":[86],"weighted":[88],"combination":[89],"FA":[92],"FR,":[94],"focusing":[95],"on":[98,119],"accurately":[99],"predicting":[100],"changes.":[102],"We":[103],"also":[104],"set":[107],"evaluation":[109],"metrics":[110],"align":[112],"better":[113],"with":[114,142],"commercial":[115],"cases.":[117],"Experiments":[118],"group":[121],"challenging":[123],"real-world":[124],"datasets":[125],"show":[126],"proposed":[129],"method":[131],"can":[132],"significantly":[133],"improve":[134],"overall":[136],"performance":[137],"same":[144],"number":[145],"parameters.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}