{"id":"https://openalex.org/W4297841387","doi":"https://doi.org/10.21437/interspeech.2022-10483","title":"Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis","display_name":"Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841387","doi":"https://doi.org/10.21437/interspeech.2022-10483"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10483","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":["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/A5100442521","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0002-4355-6629"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412669","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2171-9001"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041979971","display_name":"Yusheng Dai","orcid":"https://orcid.org/0000-0003-3211-3862"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Dai","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Kore University of Enna, Italy","Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna, Italy","institution_ids":["https://openalex.org/I246010334"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056129529","display_name":"Jingdong Chen","orcid":"https://orcid.org/0000-0003-0083-9247"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Chen","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859891","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-4164-6647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["iFlytek, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFlytek, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100412669"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1766","last_page":"1770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.982699990272522,"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":0.982699990272522,"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":0.9406999945640564,"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":0.8999999761581421,"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":0.7582108974456787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.689563512802124},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6490843892097473},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4479241371154785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44215965270996094},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28173357248306274},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.27006980776786804},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21751409769058228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582108974456787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.689563512802124},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6490843892097473},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4479241371154785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44215965270996094},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28173357248306274},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.27006980776786804},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21751409769058228}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-10483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10483","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:iris.unipa.it:10447/641413","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/641413","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"},{"id":"pmh:oai:tudelft.nl:uuid:f245d102-4dec-4da2-b913-0a632dc1b769","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:f245d102-4dec-4da2-b913-0a632dc1b769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","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/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1526392145","https://openalex.org/W1558945660","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2029199293","https://openalex.org/W2096391593","https://openalex.org/W2099731107","https://openalex.org/W2136155248","https://openalex.org/W2142075667","https://openalex.org/W2148613904","https://openalex.org/W2153773386","https://openalex.org/W2157827878","https://openalex.org/W2517616541","https://openalex.org/W2538370046","https://openalex.org/W2790326622","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2900212944","https://openalex.org/W2936774411","https://openalex.org/W2952746495","https://openalex.org/W2963197115","https://openalex.org/W2963263347","https://openalex.org/W2963785710","https://openalex.org/W2999528291","https://openalex.org/W3006974783","https://openalex.org/W3011234510","https://openalex.org/W3016011581","https://openalex.org/W3016176723","https://openalex.org/W3020336359","https://openalex.org/W3035042697","https://openalex.org/W3090571339","https://openalex.org/W3097777922","https://openalex.org/W3103003256","https://openalex.org/W3123318516","https://openalex.org/W3144810982","https://openalex.org/W3162293946","https://openalex.org/W3168662520","https://openalex.org/W4224933780","https://openalex.org/W4226071457","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W90026711","https://openalex.org/W2539140714","https://openalex.org/W82246966","https://openalex.org/W2894997731","https://openalex.org/W180632291","https://openalex.org/W2083580856","https://openalex.org/W2263479716","https://openalex.org/W2321571402","https://openalex.org/W1591608209","https://openalex.org/W2129516288"],"abstract_inverted_index":{"&lt;p&gt;In":[0],"this":[1],"paper,":[2],"we":[3,70,121],"present":[4],"the":[5,47,56,65,76,91,138,147,153,163],"updated":[6],"Audio-Visual":[7],"Speech":[8],"Recognition":[9],"(AVSR)":[10],"corpus":[11,20,45,54,77,145],"of":[12,22,75,84,126,140],"MISP2021":[13],"challenge,":[14],"a":[15,72,80,124],"large-scale":[16],"audio-visual":[17,53],"Chinese":[18,52,61],"conversational":[19,51],"consisting":[21],"141h":[23],"audio":[24,86],"and":[25,32,55,78,87,109,133,146,167],"video":[26,88,97],"data":[27,89,131],"collected":[28],"by":[29,103],"far/middle/near":[30],"microphones":[31],"far/middle":[33],"cameras":[34],"in":[35,64,90,113,157],"34":[36],"real-home":[37],"TV":[38],"rooms.":[39],"To":[40],"our":[41,44],"best":[42],"knowledge,":[43],"is":[46],"first":[48,57],"distant":[49],"multi-microphone":[50],"large":[58],"vocabulary":[59],"continuous":[60],"lip-reading":[62],"dataset":[63],"adverse":[66],"home-tv":[67],"scenario.":[68],"Moreover,":[69],"make":[71],"deep":[73],"analysis":[74,95],"conduct":[79],"comprehensive":[81],"ablation":[82],"study":[83],"all":[85],"audio-only/video-only/audiovisual":[92],"systems.":[93],"Error":[94],"shows":[96],"modality":[98],"supplement":[99],"acoustic":[100],"information":[101,112],"degraded":[102],"noise":[104],"to":[105,116,151],"reduce":[106,117],"deletion":[107],"errors":[108],"provide":[110],"discriminative":[111],"overlapping":[114],"speech":[115,158],"substitution":[118],"errors.":[119],"Finally,":[120],"also":[122,161],"design":[123],"set":[125],"experiments":[127],"such":[128],"as":[129],"frontend,":[130],"augmentation":[132],"end-to-end":[134],"models":[135],"for":[136,162],"providing":[137],"direction":[139],"potential":[141],"future":[142],"work.":[143],"The":[144],"code":[148],"are":[149],"released":[150],"promote":[152],"research":[154],"not":[155],"only":[156],"area":[159,166],"but":[160],"computer":[164],"vision":[165],"cross-disciplinary":[168],"research.&lt;/p&gt;":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2022-10-01T00:00:00"}
