{"id":"https://openalex.org/W4285044984","doi":"https://doi.org/10.21437/interspeech.2022-11368","title":"Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription","display_name":"Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4285044984","doi":"https://doi.org/10.21437/interspeech.2022-11368"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11368","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11368","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5013736436","display_name":"Xianrui Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianrui Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069749771","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-9218-9028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phil Woodland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3844","last_page":"3848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9919999837875366,"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/T10860","display_name":"Speech and Audio Processing","score":0.9901999831199646,"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":0.7925261855125427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7846919298171997},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6981839537620544},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6733053922653198},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6096147298812866},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5530710816383362},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5131390690803528},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5071301460266113},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.46778687834739685},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4495576024055481},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4290148913860321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4189970791339874},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.41804251074790955},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41795873641967773},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3300431966781616},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2507789134979248},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.22158551216125488}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7925261855125427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846919298171997},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6981839537620544},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6733053922653198},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6096147298812866},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5530710816383362},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5131390690803528},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5071301460266113},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.46778687834739685},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4495576024055481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4290148913860321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189970791339874},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41804251074790955},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41795873641967773},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3300431966781616},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2507789134979248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.22158551216125488},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11368","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11368","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Self-supervised-learning-based":[0],"pre-trained":[1],"models":[2],"for":[3,67,126,137],"speech":[4,17,27],"data,":[5],"such":[6],"as":[7],"Wav2Vec":[8],"2.0":[9],"(W2V2),":[10],"have":[11],"become":[12],"the":[13,47,91,95,100,115,132,179],"backbone":[14],"of":[15,49,86,93,153,162],"many":[16],"tasks.":[18],"In":[19],"this":[20],"paper,":[21],"to":[22,41,134,178],"achieve":[23],"speaker":[24,45,55,104,172],"diarisation":[25,147],"and":[26,54,60,75,83,106,129,156,168],"recognition":[28],"using":[29,77,122],"a":[30,33],"single":[31],"model,":[32],"tandem":[34],"multitask":[35,70],"training":[36],"(TMT)":[37],"method":[38],"is":[39,65],"proposed":[40],"fine-tune":[42],"W2V2.":[43],"For":[44],"diarisation,":[46],"tasks":[48],"voice":[50],"activity":[51],"detection":[52],"(VAD)":[53],"classification":[56,63],"(SC)":[57],"are":[58],"required,":[59],"connectionist":[61],"temporal":[62],"(CTC)":[64],"used":[66],"ASR.":[68,111],"The":[69],"framework":[71],"implements":[72],"VAD,":[73,98,127,154],"SC,":[74,128,155],"ASR":[76,130,157],"an":[78],"early":[79],"layer,":[80,82],"middle":[81],"late":[84],"layer":[85],"W2V2,":[87],"which":[88],"coincides":[89],"with":[90,97,110,164,181],"order":[92],"segmenting":[94],"audio":[96],"clustering":[99],"segments":[101],"based":[102],"on":[103,114],"embeddings,":[105],"transcribing":[107],"each":[108],"segment":[109],"Experimental":[112],"results":[113],"augmented":[116],"multi-party":[117],"(AMI)":[118],"dataset":[119],"showed":[120],"that":[121],"different":[123],"W2V2":[124],"layers":[125,136],"from":[131],"earlier":[133],"later":[135],"TMT":[138],"not":[139],"only":[140],"saves":[141],"computational":[142],"cost,":[143],"but":[144],"also":[145],"reduces":[146],"error":[148,175],"rates":[149],"(DERs).":[150],"Joint":[151],"fine-tuning":[152],"yielded":[158],"16%/17%":[159],"relative":[160],"reductions":[161,170],"DER":[163],"manual/automatic":[165],"segmentation":[166],"respectively,":[167],"consistent":[169],"in":[171],"attributed":[173],"word":[174],"rate,":[176],"compared":[177],"baseline":[180],"separately":[182],"fine-tuned":[183],"models.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}