{"id":"https://openalex.org/W4406461688","doi":"https://doi.org/10.1109/slt61566.2024.10832196","title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","display_name":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461688","doi":"https://doi.org/10.1109/slt61566.2024.10832196"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5054879184","display_name":"Yihan Wu","orcid":"https://orcid.org/0000-0002-1202-4208"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Wu","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085113833","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0001-9309-8331"},"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":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102942362","display_name":"Yichen Lu","orcid":"https://orcid.org/0000-0003-0296-3540"},"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":"Yichen Lu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"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":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505571","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0002-2163-7401"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62430996,"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":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7172492742538452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7127445936203003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3675099015235901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172492742538452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7127445936203003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675099015235901}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1593114658","https://openalex.org/W2150884987","https://openalex.org/W2551572271","https://openalex.org/W2890952074","https://openalex.org/W2899274165","https://openalex.org/W2962892438","https://openalex.org/W2964182350","https://openalex.org/W2984008963","https://openalex.org/W3035299099","https://openalex.org/W3148906368","https://openalex.org/W3162293946","https://openalex.org/W3166396011","https://openalex.org/W3205786327","https://openalex.org/W3211278025","https://openalex.org/W4284973286","https://openalex.org/W4293718192","https://openalex.org/W4296414218","https://openalex.org/W4311000453","https://openalex.org/W4319862255","https://openalex.org/W4372260033","https://openalex.org/W4385822890","https://openalex.org/W4386076133","https://openalex.org/W4388017359","https://openalex.org/W4391021675","https://openalex.org/W4391376671","https://openalex.org/W4393150371","https://openalex.org/W4402112192","https://openalex.org/W6635221813","https://openalex.org/W6732520560","https://openalex.org/W6755559483","https://openalex.org/W6791353385","https://openalex.org/W6804209468","https://openalex.org/W6839026989","https://openalex.org/W6847363464","https://openalex.org/W6861475616"],"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":{"Visual":[0],"signals":[1],"can":[2],"enhance":[3],"audiovisual":[4,20],"speech":[5,21,51,70,84],"recognition":[6,22,52,85],"accuracy":[7],"by":[8,72],"providing":[9],"additional":[10],"contextual":[11],"information.":[12],"Given":[13],"the":[14,43,102,121],"complexity":[15],"of":[16,124],"visual":[17,60,63,94,99],"signals,":[18],"an":[19],"model":[23,104,112],"requires":[24],"robust":[25,50,82],"generalization":[26,89,122],"capabilities":[27],"across":[28,126],"diverse":[29,127],"video":[30,128],"scenarios,":[31],"presenting":[32],"a":[33,73,81,106],"significant":[34],"challenge.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,57,77,97],"introduce":[40],"EVA,":[41],"leveraging":[42],"mixture-of-Experts":[44],"for":[45,53],"audioVisual":[46],"ASR":[47,103],"to":[48,92],"perform":[49],"\u201cin-the-wild\u201d":[54],"videos.":[55],"Specifically,":[56],"first":[58],"encode":[59],"information":[61,95,100],"into":[62,69,101],"tokens":[64],"sequence":[65],"and":[66],"map":[67],"them":[68],"space":[71],"lightweight":[74],"projection.":[75],"Then,":[76],"build":[78],"EVA":[79,125],"upon":[80],"pretrained":[83],"model,":[86],"ensuring":[87],"its":[88],"ability.":[90],"Moreover,":[91],"incorporate":[93],"effectively,":[96],"inject":[98],"through":[105],"mixture-of-experts":[107],"module.":[108],"Experiments":[109],"show":[110],"our":[111],"achieves":[113],"state-of-the-art":[114],"results":[115],"on":[116],"three":[117],"benchmarks,":[118],"which":[119],"demonstrates":[120],"ability":[123],"domains.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}