{"id":"https://openalex.org/W4392903825","doi":"https://doi.org/10.1109/icassp48485.2024.10446769","title":"MLCA-AVSR: Multi-Layer Cross Attention Fusion Based Audio-Visual Speech Recognition","display_name":"MLCA-AVSR: Multi-Layer Cross Attention Fusion Based Audio-Visual Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903825","doi":"https://doi.org/10.1109/icassp48485.2024.10446769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5101808140","display_name":"Wang He","orcid":"https://orcid.org/0000-0002-3436-1299"},"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":"He Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"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":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693197","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0002-8629-4622"},"institutions":[{"id":"https://openalex.org/I3148377317","display_name":"Department of Space","ror":"https://ror.org/000kjq947","country_code":"IN","type":"government","lineage":["https://openalex.org/I3148377317"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Li Auto,Space AI","Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Li Auto,Space AI","institution_ids":["https://openalex.org/I3148377317"]},{"raw_affiliation_string":"Space AI, Li Auto","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"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":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5944,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.98589246,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8150","last_page":"8154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.7458097338676453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233251333236694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.578302800655365},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5675654411315918},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5509570240974426},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47386932373046875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4155173599720001},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.411319375038147}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7458097338676453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233251333236694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578302800655365},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5675654411315918},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5509570240974426},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47386932373046875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4155173599720001},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.411319375038147},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W1983812858","https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2526425061","https://openalex.org/W2759071281","https://openalex.org/W2889624961","https://openalex.org/W2900212944","https://openalex.org/W2962780374","https://openalex.org/W3097777922","https://openalex.org/W3102469722","https://openalex.org/W3162249256","https://openalex.org/W3162293946","https://openalex.org/W3196777808","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4297841387","https://openalex.org/W4319586547","https://openalex.org/W4319862255","https://openalex.org/W4372260021","https://openalex.org/W4372267507","https://openalex.org/W4372270419","https://openalex.org/W4372317224","https://openalex.org/W4372346152","https://openalex.org/W4375868974","https://openalex.org/W4375869051","https://openalex.org/W4385245566","https://openalex.org/W4386071467","https://openalex.org/W6688816777","https://openalex.org/W6781364056","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W1911859126","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2120730869","https://openalex.org/W2544241817"],"abstract_inverted_index":{"While":[0],"automatic":[1],"speech":[2,12],"recognition":[3,13],"(ASR)":[4],"systems":[5,15],"degrade":[6],"significantly":[7],"in":[8,133],"noisy":[9],"environments,":[10],"audio-visual":[11],"(AVSR)":[14],"aim":[16],"to":[17,119],"complement":[18],"the":[19,28,38,43,50,54,90,95,113,130,134,137,146],"audio":[20],"stream":[21],"with":[22,124],"noise-invariant":[23],"visual":[24],"cues":[25],"and":[26,116],"improve":[27],"system\u2019s":[29],"robustness.":[30],"However,":[31],"current":[32],"studies":[33],"mainly":[34],"focus":[35],"on":[36,89,112,156],"fusing":[37,79],"well-learned":[39],"modality":[40,55,77],"features,":[41],"like":[42],"output":[44],"of":[45,75,84,97,110,139,154],"modality-specific":[46],"encoders,":[47],"without":[48],"considering":[49],"contextual":[51],"relationship":[52],"during":[53],"feature":[56],"learning.":[57],"In":[58],"this":[59,157],"study,":[60],"we":[61],"propose":[62],"a":[63,102,150],"multi-layer":[64],"cross-attention":[65],"fusion":[66,138],"based":[67],"AVSR":[68],"(MLCA-AVSR)":[69],"approach":[70,144],"that":[71],"promotes":[72],"representation":[73],"learning":[74],"each":[76],"by":[78],"them":[80],"at":[81],"different":[82],"levels":[83],"audio/visual":[85],"encoders.":[86],"Experimental":[87],"results":[88],"MISP2022-AVSR":[91],"Challenge":[92],"dataset":[93],"show":[94],"efficacy":[96],"our":[98,125,142],"proposed":[99,143],"system,":[100,148],"achieving":[101],"concatenated":[103],"minimum":[104],"permutation":[105],"character":[106],"error":[107],"rate":[108],"(cpCER)":[109],"30.57%":[111],"Eval":[114],"set":[115],"yielding":[117],"up":[118],"3.17%":[120],"relative":[121],"improvement":[122],"compared":[123],"previous":[126],"system":[127],"which":[128],"ranked":[129],"second":[131],"place":[132],"challenge.":[135],"Following":[136],"multiple":[140],"systems,":[141],"surpasses":[145],"first-place":[147],"establishing":[149],"new":[151],"SOTA":[152],"cpCER":[153],"29.13%":[155],"dataset.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-03-19T00:00:00"}