{"id":"https://openalex.org/W4372349800","doi":"https://doi.org/10.1109/icassp49357.2023.10095295","title":"A Sidecar Separator Can Convert A Single-Talker Speech Recognition System to A Multi-Talker One","display_name":"A Sidecar Separator Can Convert A Single-Talker Speech Recognition System to A Multi-Talker One","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349800","doi":"https://doi.org/10.1109/icassp49357.2023.10095295"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095295","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":"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/A5031382920","display_name":"Lingwei Meng","orcid":null},"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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, 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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632921","display_name":"Yuejiao Wang","orcid":"https://orcid.org/0000-0001-5910-9439"},"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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, 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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, 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,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, 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":3.8666,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95677132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9933000206947327,"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":0.6449117660522461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6355416774749756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449117660522461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6355416774749756}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095295","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":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2069681747","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2890244912","https://openalex.org/W2933138175","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963477857","https://openalex.org/W3015412285","https://openalex.org/W3015746570","https://openalex.org/W3015834770","https://openalex.org/W3017474798","https://openalex.org/W3027008958","https://openalex.org/W3034273309","https://openalex.org/W3036601975","https://openalex.org/W3094821064","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3121914243","https://openalex.org/W3137249133","https://openalex.org/W3186652349","https://openalex.org/W3196194966","https://openalex.org/W3198522318","https://openalex.org/W3198763610","https://openalex.org/W4226033575","https://openalex.org/W4226380987","https://openalex.org/W4226491018","https://openalex.org/W4320086272","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6788328058","https://openalex.org/W6838662218","https://openalex.org/W6846678071"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Although":[0],"automatic":[1],"speech":[2,17,73],"recognition":[3,18],"(ASR)":[4],"can":[5],"perform":[6],"well":[7],"in":[8,14],"common":[9],"non-overlapping":[10],"environments,":[11],"sustaining":[12],"performance":[13],"multi-talker":[15,67],"overlapping":[16],"remains":[19],"challenging.":[20],"Recent":[21],"research":[22],"revealed":[23],"that":[24],"ASR":[25,64,85],"model\u2019s":[26],"encoder":[27],"captures":[28],"different":[29,34],"levels":[30],"of":[31,95,107,133],"information":[32],"with":[33,81,87],"layers":[35,39,49],"\u2013":[36],"the":[37,47,71,93,96,102,110,114,122],"lower":[38],"tend":[40],"to":[41,55,60],"have":[42],"more":[43,50],"acoustic":[44],"information,":[45],"and":[46,99,135],"upper":[48],"linguistic.":[51],"This":[52],"inspires":[53],"us":[54],"develop":[56],"a":[57,62,82,88,118,128],"Sidecar":[58,89,103],"separator":[59],"empower":[61],"well-trained":[63],"model":[65,86,98],"for":[66,121,140],"scenarios":[68],"by":[69,117],"separating":[70],"mixed":[72,124],"embedding":[74],"between":[75],"two":[76],"suitable":[77],"layers.":[78],"We":[79],"experimented":[80],"wav2vec":[83],"2.0-based":[84],"mounted.":[90],"By":[91],"freezing":[92],"parameters":[94],"original":[97],"training":[100],"only":[101],"(8.7":[104],"M,":[105],"8.4%":[106],"all":[108],"parameters),":[109],"proposed":[111],"approach":[112],"outperforms":[113],"previous":[115],"state-of-the-art":[116],"large":[119],"margin":[120],"2-speaker":[123],"LibriMix":[125],"dataset,":[126],"reaching":[127],"word":[129],"error":[130],"rate":[131],"(WER)":[132],"10.36%;":[134],"obtains":[136],"comparable":[137],"results":[138],"(7.56%)":[139],"LibriSpeechMix":[141],"dataset":[142],"when":[143],"limited":[144],"training.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}