{"id":"https://openalex.org/W4283461667","doi":"https://doi.org/10.21437/interspeech.2022-696","title":"Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems","display_name":"Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283461667","doi":"https://doi.org/10.21437/interspeech.2022-696"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-696","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-696","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.11596","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100938995","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0002-2672-2461"},"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"],"raw_orcid":null,"affiliations":[{"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/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"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":"Jiajun Deng","raw_affiliation_strings":["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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045355404","display_name":"Shoukang Hu","orcid":"https://orcid.org/0000-0002-3345-6923"},"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":"Shoukang Hu","raw_affiliation_strings":["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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113476082","display_name":"Xurong Xie","orcid":"https://orcid.org/0009-0007-6729-2879"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"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":"Tianzi Wang","raw_affiliation_strings":["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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"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":"Shujie Hu","raw_affiliation_strings":["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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"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":"Mengzhe Geng","raw_affiliation_strings":["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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100943655","display_name":"Boyang Xue","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":"Boyang Xue","raw_affiliation_strings":["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"]}]},{"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, 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"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3158","last_page":"3162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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/T11447","display_name":"Blind Source Separation Techniques","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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/decoding-methods","display_name":"Decoding methods","score":0.7067158818244934},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7064728736877441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953614950180054},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6207736134529114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5633249282836914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41856786608695984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3279799818992615},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18448898196220398},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07767924666404724},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0689941942691803}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7067158818244934},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7064728736877441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953614950180054},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6207736134529114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5633249282836914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41856786608695984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3279799818992615},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18448898196220398},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07767924666404724},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0689941942691803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-696","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-696","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"},{"id":"pmh:oai:arXiv.org:2206.11596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.11596","pdf_url":"https://arxiv.org/pdf/2206.11596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.11596","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.11596","pdf_url":"https://arxiv.org/pdf/2206.11596","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W136679770","https://openalex.org/W160722039","https://openalex.org/W173561343","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1904457459","https://openalex.org/W2016185147","https://openalex.org/W2046932483","https://openalex.org/W2047012355","https://openalex.org/W2081323593","https://openalex.org/W2094147890","https://openalex.org/W2100734170","https://openalex.org/W2103127925","https://openalex.org/W2113094193","https://openalex.org/W2113344693","https://openalex.org/W2115585811","https://openalex.org/W2124912321","https://openalex.org/W2128176022","https://openalex.org/W2131342762","https://openalex.org/W2142499181","https://openalex.org/W2143612262","https://openalex.org/W2155273149","https://openalex.org/W2166637769","https://openalex.org/W2239847623","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2407299475","https://openalex.org/W2514741789","https://openalex.org/W2542851870","https://openalex.org/W2567070169","https://openalex.org/W2784367312","https://openalex.org/W2888867175","https://openalex.org/W2936774411","https://openalex.org/W2939173691","https://openalex.org/W2972692349","https://openalex.org/W2972818416","https://openalex.org/W2973122799","https://openalex.org/W3007905516","https://openalex.org/W3094780479","https://openalex.org/W3097777922","https://openalex.org/W3113244915","https://openalex.org/W3161375121","https://openalex.org/W3163793923","https://openalex.org/W3198654230","https://openalex.org/W4283654390","https://openalex.org/W4287816637","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2161474341","https://openalex.org/W2997567050","https://openalex.org/W4302615923","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W4220731478"],"abstract_inverted_index":{"Fundamental":[0],"modelling":[1],"differences":[2],"between":[3],"hybrid":[4,33,44,89],"and":[5,16,25,35,53,165],"end-to-end":[6],"(E2E)":[7],"automatic":[8],"speech":[9],"recognition":[10],"(ASR)":[11],"systems":[12,115],"create":[13],"large":[14],"diversity":[15],"complementarity":[17],"among":[18],"them.":[19],"This":[20],"paper":[21],"investigates":[22],"multi-pass":[23,41,135],"rescoring":[24,136],"cross":[26,81,86],"adaptation":[27,61],"based":[28],"system":[29,48,77,82,91,101,122,132,159],"combination":[30,123],"approaches":[31,124],"for":[32],"TDNN":[34],"Conformer":[36,76,100,158],"E2E":[37],"ASR":[38],"systems.":[39,128],"In":[40,85],"rescoring,":[42],"state-of-the-art":[43],"LF-MMI":[45],"trained":[46],"CNN-TDNN":[47,90],"featuring":[49],"speed":[50],"perturbation,":[51],"SpecAugment":[52],"Bayesian":[54],"learning":[55],"hidden":[56],"unit":[57],"contributions":[58],"(LHUC)":[59],"speaker":[60,74],"was":[62,92],"used":[63],"to":[64,94,147,151],"produce":[65],"initial":[66],"N-best":[67],"outputs":[68],"before":[69],"being":[70],"rescored":[71],"by":[72],"the":[73,88,95,99,107,113,120,126,155,161],"adapted":[75,93],"using":[78,117,134],"a":[79],"2-way":[80],"score":[83],"interpolation.":[84],"adaptation,":[87],"1-best":[96],"output":[97],"of":[98,119,145],"or":[102],"vice":[103],"versa.":[104],"Experiments":[105],"on":[106,160],"300-hour":[108],"Switchboard":[109],"corpus":[110],"suggest":[111],"that":[112],"combined":[114,131],"derived":[116],"either":[118],"two":[121],"outperformed":[125],"individual":[127],"The":[129],"best":[130],"obtained":[133],"produced":[137],"statistically":[138],"significant":[139],"word":[140],"error":[141],"rate":[142],"(WER)":[143],"reductions":[144],"2.5%":[146],"3.9%":[148],"absolute":[149],"(22.5%":[150],"28.9%":[152],"relative)":[153],"over":[154],"stand":[156],"alone":[157],"NIST":[162],"Hub5'00,":[163],"Rt03":[164],"Rt02":[166],"evaluation":[167],"data.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2022-06-26T00:00:00"}
