{"id":"https://openalex.org/W4408352376","doi":"https://doi.org/10.1109/icassp49660.2025.10888841","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","display_name":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352376","doi":"https://doi.org/10.1109/icassp49660.2025.10888841"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5062761975","display_name":"Jiawen Kang","orcid":"https://orcid.org/0000-0002-8218-3490"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiawen Kang","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089153961","display_name":"Lingwei Meng","orcid":"https://orcid.org/0000-0003-1028-6017"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingwei Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065896539","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0001-9781-9407"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingyu Cui","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061240757","display_name":"Yuejiao Wang","orcid":"https://orcid.org/0000-0002-8221-8841"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuejiao Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79025965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9922999739646912,"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":0.9922999739646912,"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":0.9828000068664551,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9093999862670898,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7370816469192505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7343050837516785},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6263958215713501},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4500126242637634}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7370816469192505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343050837516785},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6263958215713501},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4500126242637634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2105594594","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2766219058","https://openalex.org/W2962780374","https://openalex.org/W2963414781","https://openalex.org/W2963477857","https://openalex.org/W2963773971","https://openalex.org/W3013139777","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3097643313","https://openalex.org/W3109079702","https://openalex.org/W3177132412","https://openalex.org/W3207834622","https://openalex.org/W4221165341","https://openalex.org/W4221165543","https://openalex.org/W4224925136","https://openalex.org/W4226491018","https://openalex.org/W4372349800","https://openalex.org/W4385822334","https://openalex.org/W4385822384","https://openalex.org/W4387010481","https://openalex.org/W4391021535","https://openalex.org/W4392902710","https://openalex.org/W4392904528","https://openalex.org/W4402111585","https://openalex.org/W4402116591","https://openalex.org/W4408352078","https://openalex.org/W6845608264","https://openalex.org/W6857305603"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Multi-talker":[0],"speech":[1,119,158],"recognition":[2,159],"(MTASR)":[3],"faces":[4],"unique":[5],"challenges":[6],"in":[7,27,51,156],"disentangling":[8],"and":[9,132],"transcribing":[10],"overlapping":[11],"speech.":[12,136],"To":[13],"address":[14],"these":[15],"challenges,":[16],"this":[17,59],"paper":[18],"investigates":[19],"the":[20,45,72,93,108],"role":[21],"of":[22,55,118,129,143],"Connectionist":[23],"Temporal":[24],"Classification":[25],"(CTC)":[26],"speaker":[28,89,154],"disentanglement":[29,90,155],"when":[30],"incorporated":[31],"with":[32,106],"Serialized":[33],"Output":[34],"Training":[35],"(SOT)":[36],"for":[37,83,146],"MTASR.":[38],"Our":[39],"visualization":[40],"reveals":[41],"that":[42],"CTC":[43,66,75,81],"guides":[44],"encoder":[46,94],"to":[47,95],"represent":[48,96],"different":[49,97],"speakers":[50],"distinct":[52],"temporal":[53],"regions":[54],"acoustic":[56],"embeddings.":[57],"Leveraging":[58],"insight,":[60],"we":[61,122],"propose":[62],"a":[63,79,150],"novel":[64],"Speaker-Aware":[65],"(SACTC)":[67],"training":[68],"objective,":[69],"based":[70],"on":[71,134,153],"Bayes":[73],"risk":[74],"framework.":[76],"SACTC":[77],"is":[78],"tailored":[80],"variant":[82],"multi-talker":[84,157],"scenarios,":[85],"it":[86],"explicitly":[87],"models":[88],"by":[91],"constraining":[92],"speakers\u2019":[98],"tokens":[99],"at":[100],"specific":[101],"time":[102],"frames.":[103],"When":[104],"integrated":[105],"SOT,":[107],"SOT-SACTC":[109],"model":[110],"consistently":[111],"outperforms":[112],"standard":[113],"SOT-CTC":[114],"across":[115],"various":[116],"degrees":[117],"overlap.":[120],"Specifically,":[121],"observe":[123],"relative":[124],"word":[125],"error":[126],"rate":[127],"reductions":[128],"10%":[130],"overall":[131],"15%":[133],"low-overlap":[135],"This":[137],"work":[138],"represents":[139],"an":[140],"initial":[141],"exploration":[142],"CTC-based":[144],"enhancements":[145],"MTASR":[147],"tasks,":[148],"offering":[149],"new":[151],"perspective":[152],".1":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
