{"id":"https://openalex.org/W4392902880","doi":"https://doi.org/10.1109/icassp48485.2024.10445900","title":"Improving Multi-Speaker ASR With Overlap-Aware Encoding And Monotonic Attention","display_name":"Improving Multi-Speaker ASR With Overlap-Aware Encoding And Monotonic Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902880","doi":"https://doi.org/10.1109/icassp48485.2024.10445900"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445900","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100455266","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-9910-2573"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033829994","display_name":"Feng Wang","orcid":"https://orcid.org/0000-0002-3492-3714"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310824","display_name":"Wenhao Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110791301","display_name":"Lingyan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyan Huang","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"12416","last_page":"12420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.842741847038269},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.735958456993103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6334306597709656},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6272509098052979},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5415793061256409},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46543848514556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4125481843948364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842741847038269},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.735958456993103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6334306597709656},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6272509098052979},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5415793061256409},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46543848514556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4125481843948364},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445900","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1141457816","display_name":null,"funder_award_id":"20720210087","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2122364000","https://openalex.org/W2962780374","https://openalex.org/W2963351448","https://openalex.org/W2963773971","https://openalex.org/W3013139777","https://openalex.org/W3018242354","https://openalex.org/W3023126978","https://openalex.org/W3032969657","https://openalex.org/W3097777922","https://openalex.org/W3143843080","https://openalex.org/W3162354890","https://openalex.org/W3171066367","https://openalex.org/W3196117288","https://openalex.org/W3207834622","https://openalex.org/W4224925136","https://openalex.org/W4226491018","https://openalex.org/W4281926863","https://openalex.org/W4319862683","https://openalex.org/W4372349800","https://openalex.org/W4375868938","https://openalex.org/W4385573729","https://openalex.org/W4385822334","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"multi-speaker":[2],"speech":[3,31,65],"recognition":[4],"with":[5,81],"the":[6,21,27,35,58,70,73,85,96,101,109],"serialized":[7],"output":[8],"training":[9],"(SOT)":[10],"strategy":[11],"demonstrates":[12],"good":[13],"performance":[14],"in":[15],"modeling":[16,28],"diverse":[17],"speaker":[18],"scenarios.":[19],"However,":[20],"E2E":[22],"architecture":[23],"doesn\u2019t":[24],"explicitly":[25],"address":[26],"of":[29,87,103],"overlapping":[30,64],"areas,":[32],"potentially":[33],"limiting":[34],"model\u2019s":[36,110],"ability":[37],"to":[38,60,75],"generalize.":[39],"To":[40],"tackle":[41],"this":[42],"issue,":[43],"we":[44],"introduce":[45],"two":[46,105],"approaches:":[47],"overlap-aware":[48],"encoding":[49],"method":[50],"and":[51],"monotonic":[52],"attention":[53,78,86],"loss.":[54],"The":[55],"former":[56],"enables":[57],"model":[59,74],"acquire":[61],"knowledge":[62],"about":[63],"through":[66],"multitask":[67],"learning,":[68],"while":[69],"latter":[71],"encourages":[72],"learn":[76],"specific":[77],"patterns":[79],"associated":[80],"overlap":[82],"by":[83],"constraining":[84],"adjacent":[88],"text":[89],"time":[90],"steps.":[91],"Our":[92],"experimental":[93],"results":[94],"on":[95],"AliMeeting":[97],"dataset":[98],"show":[99],"that":[100],"combination":[102],"these":[104],"methods":[106],"effectively":[107],"enhances":[108],"performance.":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
