{"id":"https://openalex.org/W4392903670","doi":"https://doi.org/10.1109/icassp48485.2024.10447487","title":"Hourglass-AVSR: Down-Up Sampling-Based Computational Efficiency Model for Audio-Visual Speech Recognition","display_name":"Hourglass-AVSR: Down-Up Sampling-Based Computational Efficiency Model for Audio-Visual Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903670","doi":"https://doi.org/10.1109/icassp48485.2024.10447487"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447487","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":"article","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/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016797242","display_name":"Haoxu Wang","orcid":"https://orcid.org/0000-0002-5430-0899"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055433405","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0001-9053-9314"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy,China","Speech Lab of DAMO Academy, Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100616400"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65181774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7940","last_page":"7944"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9927999973297119,"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":0.747933030128479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6885402202606201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5331413745880127},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5054924488067627},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46182045340538025},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46173039078712463},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42590415477752686},{"id":"https://openalex.org/keywords/hourglass","display_name":"Hourglass","score":0.4209528863430023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36719340085983276},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3425975441932678},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11174437403678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747933030128479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6885402202606201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331413745880127},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5054924488067627},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46182045340538025},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46173039078712463},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42590415477752686},{"id":"https://openalex.org/C127532173","wikidata":"https://www.wikidata.org/wiki/Q179904","display_name":"Hourglass","level":2,"score":0.4209528863430023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36719340085983276},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3425975441932678},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11174437403678894},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447487","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1876378865","https://openalex.org/W2194775991","https://openalex.org/W2289925289","https://openalex.org/W2551572271","https://openalex.org/W2593722617","https://openalex.org/W2883429621","https://openalex.org/W2884797191","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2915347754","https://openalex.org/W2963155035","https://openalex.org/W2963308316","https://openalex.org/W2963654155","https://openalex.org/W2990152177","https://openalex.org/W3006974783","https://openalex.org/W3035042697","https://openalex.org/W3102469722","https://openalex.org/W3162293946","https://openalex.org/W3196777808","https://openalex.org/W3207834622","https://openalex.org/W3211278025","https://openalex.org/W4224916606","https://openalex.org/W4224925136","https://openalex.org/W4224933780","https://openalex.org/W4225304491","https://openalex.org/W4297841387","https://openalex.org/W4372260021","https://openalex.org/W4375868974","https://openalex.org/W4375869051","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6682864246","https://openalex.org/W6781364056","https://openalex.org/W6839026989"],"related_works":["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/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Recently":[0],"audio-visual":[1,45],"speech":[2,16],"recognition":[3,17,91],"(AVSR),":[4],"which":[5,93],"better":[6],"leverages":[7],"video":[8,85,106],"modality":[9,134],"as":[10,35],"additional":[11],"information":[12,96,103],"to":[13,33,59,88,131,178],"extend":[14],"automatic":[15],"(ASR),":[18],"has":[19],"shown":[20],"promising":[21],"results":[22],"in":[23,189],"complex":[24,36],"acoustic":[25],"environments.":[26],"However,":[27],"there":[28],"is":[29,68],"still":[30],"substantial":[31],"space":[32],"improve":[34,89],"computation":[37,209],"of":[38,44,199],"visual":[39,98,138,193],"modules":[40],"and":[41,63,82,100,158,171],"ineffective":[42],"fusion":[43,130],"modalities.":[46],"To":[47],"eliminate":[48],"these":[49],"drawbacks,":[50],"we":[51,78,109,125],"propose":[52,79,126],"a":[53,80,111,127],"down-up":[54,201],"sampling-based":[55],"AVSR":[56,181],"model":[57,152,155,184,205],"(Hourglass-AVSR)":[58],"enjoy":[60],"high":[61],"efficiency":[62],"performance,":[64,92],"whose":[65],"time":[66],"length":[67],"scaled":[69],"during":[70,115],"the":[71,90,116,133,144,186,192,197],"intermediate":[72],"processing,":[73],"resembling":[74],"an":[75],"hourglass.":[76],"Firstly,":[77],"context":[81],"residual":[83,102],"aware":[84],"upsampling":[86,117],"approach":[87,114],"utilizes":[94],"contextual":[95],"from":[97],"representations":[99],"captures":[101],"between":[104],"adjacent":[105],"frames.":[107],"Secondly,":[108],"introduce":[110],"visual-audio":[112],"alignment":[113],"by":[118,156],"explicitly":[119],"incorporating":[120],"boundary":[121],"constraint":[122],"loss.":[123],"Besides,":[124],"cross-layer":[128],"attention":[129],"capture":[132],"dependencies":[135],"within":[136],"each":[137],"encoder":[139],"layer.":[140],"Experiments":[141],"conducted":[142],"on":[143,169,196],"MISP-AVSR":[145],"dataset":[146],"reveal":[147],"that":[148],"our":[149,183,200],"proposed":[150],"Hourglass-AVSR":[151,204],"outperforms":[153],"ASR":[154],"12.9%":[157],"20.8%":[159],"relative":[160],"concatenated":[161],"minimum":[162],"permutation":[163],"character":[164],"error":[165],"rate":[166],"(cpCER)":[167],"reduction":[168],"far-field":[170],"middle-field":[172],"test":[173],"sets,":[174],"respectively.":[175],"Moreover,":[176],"compared":[177],"other":[179],"state-of-the-art":[180],"models,":[182],"exhibits":[185],"highest":[187],"improvement":[188],"cpCER":[190],"for":[191],"module.":[194],"Furthermore,":[195],"benefit":[198],"sampling":[202],"approach,":[203],"reduces":[206],"54.2%":[207],"overall":[208],"costs":[210],"with":[211],"minor":[212],"performance":[213],"degradation.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}