{"id":"https://openalex.org/W3162354890","doi":"https://doi.org/10.1109/icassp39728.2021.9414432","title":"Hypothesis Stitcher for End-to-End Speaker-Attributed ASR on Long-Form Multi-Talker Recordings","display_name":"Hypothesis Stitcher for End-to-End Speaker-Attributed ASR on Long-Form Multi-Talker Recordings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162354890","doi":"https://doi.org/10.1109/icassp39728.2021.9414432","mag":"3162354890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"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":true,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corp.,USA","Microsoft Corp., USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corp.,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5050058892"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8425698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6763","last_page":"6767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.8240801095962524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7611081600189209},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6917131543159485},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6794391870498657},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6608718633651733},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5415627360343933},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5059379935264587},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4951077997684479},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4828101396560669},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4430428743362427},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4320371747016907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3546076714992523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1406824290752411},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0834667980670929}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8240801095962524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611081600189209},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6917131543159485},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6794391870498657},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6608718633651733},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5415627360343933},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5059379935264587},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4951077997684479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4828101396560669},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4430428743362427},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4320371747016907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3546076714992523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1406824290752411},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0834667980670929},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1591607137","https://openalex.org/W1876378865","https://openalex.org/W2125336414","https://openalex.org/W2569324142","https://openalex.org/W2900440209","https://openalex.org/W2963403868","https://openalex.org/W2972492143","https://openalex.org/W2973127116","https://openalex.org/W3007946293","https://openalex.org/W3008181812","https://openalex.org/W3008283340","https://openalex.org/W3008898571","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3021984791","https://openalex.org/W3025834604","https://openalex.org/W3094821064","https://openalex.org/W3095822285","https://openalex.org/W3097643313","https://openalex.org/W3131736947","https://openalex.org/W3143843080","https://openalex.org/W3149629662","https://openalex.org/W4237168004","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6639431793","https://openalex.org/W6739901393","https://openalex.org/W6775537894","https://openalex.org/W6776544788","https://openalex.org/W6782161367","https://openalex.org/W6791127467"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2499802997","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W4255044973","https://openalex.org/W2890936991"],"abstract_inverted_index":{"An":[0],"end-to-end":[1],"(E2E)":[2],"speaker-attributed":[3,27],"automatic":[4],"speech":[5,17,35],"recognition":[6,18],"(SA-ASR)":[7],"model":[8,23,68,121,155],"was":[9,93],"proposed":[10,173],"recently":[11],"to":[12,49,61,95,102],"jointly":[13],"perform":[14,96],"speaker":[15,20],"counting,":[16],"and":[19,55,138,156,167],"identification.":[21],"The":[22,120],"achieved":[24],"a":[25,88,110,114,142],"low":[26],"word":[28],"error":[29],"rate":[30],"(SA-WER)":[31],"for":[32,71,99,179],"monaural":[33],"overlapped":[34],"comprising":[36],"an":[37],"unknown":[38],"number":[39],"of":[40,151],"speakers.":[41],"However,":[42],"the":[43,50,53,65,134,152,160,172],"E2E":[44,66,104],"modeling":[45],"approach":[46],"is":[47],"susceptible":[48],"mismatch":[51],"between":[52],"training":[54],"testing":[56],"conditions.":[57],"It":[58],"has":[59],"yet":[60],"be":[62],"investigated":[63],"whether":[64],"SA-ASR":[67,105],"works":[69],"well":[70],"recordings":[72],"that":[73,92,130,171],"are":[74,131],"much":[75],"longer":[76],"than":[77],"samples":[78],"seen":[79],"during":[80],"training.":[81],"In":[82],"this":[83],"work,":[84],"we":[85,108],"first":[86],"apply":[87],"known":[89],"decoding":[90,162],"technique":[91],"developed":[94],"single-speaker":[97],"ASR":[98],"long-form":[100,136,180],"audio":[101,128],"our":[103],"task.":[106],"Then,":[107],"propose":[109,147],"novel":[111],"method":[112,174],"using":[113,165],"sequence-to-sequence":[115],"model,":[116],"called":[117],"hypothesis":[118,153],"stitcher.":[119],"takes":[122],"multiple":[123],"hypotheses":[124],"obtained":[125],"from":[126,133],"short":[127],"segments":[129],"extracted":[132],"original":[135],"input,":[137],"it":[139],"then":[140],"outputs":[141],"fused":[143],"single":[144],"hypothesis.":[145],"We":[146],"several":[148],"architectural":[149],"variations":[150],"stitcher":[154],"compare":[157],"them":[158],"with":[159],"conventional":[161],"methods.":[163],"Experiments":[164],"LibriSpeech":[166],"LibriCSS":[168],"corpora":[169],"show":[170],"significantly":[175],"improves":[176],"SA-WER":[177],"especially":[178],"multi-talker":[181],"recordings.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}