{"id":"https://openalex.org/W4385767994","doi":"https://doi.org/10.24963/ijcai.2023/564","title":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","display_name":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767994","doi":"https://doi.org/10.24963/ijcai.2023/564"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/564","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/564","pdf_url":"https://www.ijcai.org/proceedings/2023/0564.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0564.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018741641","display_name":"Ruizhe Li","orcid":"https://orcid.org/0000-0003-2512-845X"},"institutions":[{"id":"https://openalex.org/I195460627","display_name":"University of Aberdeen","ror":"https://ror.org/016476m91","country_code":"GB","type":"education","lineage":["https://openalex.org/I195460627"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruizhe Li","raw_affiliation_strings":["University of Aberdeen, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Aberdeen, UK","institution_ids":["https://openalex.org/I195460627"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418370","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-7587-3314"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023152132","display_name":"Heqing Zou","orcid":"https://orcid.org/0000-0003-0038-2822"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Heqing Zou","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045966396","display_name":"Qiushi Zhu","orcid":"https://orcid.org/0000-0002-1196-7781"},"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":"Qiushi Zhu","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":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074544822"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.9125,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86829873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5076","last_page":"5084"},"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":0.9987999796867371,"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":0.991599977016449,"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":0.7603287696838379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7415948510169983},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6648876070976257},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6428256034851074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516576886177063},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49343839287757874},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4425103962421417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3801349401473999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0704856812953949},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06742280721664429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603287696838379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7415948510169983},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6648876070976257},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6428256034851074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516576886177063},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49343839287757874},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4425103962421417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3801349401473999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0704856812953949},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06742280721664429},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/564","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/564","pdf_url":"https://www.ijcai.org/proceedings/2023/0564.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/564","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/564","pdf_url":"https://www.ijcai.org/proceedings/2023/0564.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767994.pdf"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1836465849","https://openalex.org/W1966000599","https://openalex.org/W1981276685","https://openalex.org/W2014621385","https://openalex.org/W2156387975","https://openalex.org/W2157364932","https://openalex.org/W2219249508","https://openalex.org/W2275684548","https://openalex.org/W2584992898","https://openalex.org/W2766219058","https://openalex.org/W2790326622","https://openalex.org/W2806654253","https://openalex.org/W2890052321","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2892611740","https://openalex.org/W2947476638","https://openalex.org/W2952746495","https://openalex.org/W2963785710","https://openalex.org/W2964051877","https://openalex.org/W2979476256","https://openalex.org/W2987346570","https://openalex.org/W2997540481","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3020933450","https://openalex.org/W3024509792","https://openalex.org/W3025165719","https://openalex.org/W3032514799","https://openalex.org/W3035042697","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3130492967","https://openalex.org/W3130662682","https://openalex.org/W3162293946","https://openalex.org/W3169801598","https://openalex.org/W3175300676","https://openalex.org/W3184735396","https://openalex.org/W3205173298","https://openalex.org/W4221141682","https://openalex.org/W4221153068","https://openalex.org/W4221153521","https://openalex.org/W4221167445","https://openalex.org/W4224221948","https://openalex.org/W4224319127","https://openalex.org/W4224932526","https://openalex.org/W4226244164","https://openalex.org/W4285595742","https://openalex.org/W4297841641","https://openalex.org/W4312763854","https://openalex.org/W4312877428","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6748768262","https://openalex.org/W6790825729","https://openalex.org/W6803771590","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4387678054","https://openalex.org/W4306784355","https://openalex.org/W2784004155","https://openalex.org/W4246226292","https://openalex.org/W2150768546"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,18,57],"recognition":[2,19,58],"(AVSR)":[3],"research":[4],"has":[5],"gained":[6],"a":[7,65,92,108,122],"great":[8],"success":[9],"recently":[10],"by":[11,37],"improving":[12],"the":[13,32,44,78,98,114,146],"noise-robustness":[14],"of":[15,125],"audio-only":[16],"automatic":[17],"(ASR)":[20],"with":[21],"noise-invariant":[22],"visual":[23,35],"information.":[24],"However,":[25],"most":[26],"existing":[27],"AVSR":[28],"approaches":[29],"simply":[30],"fuse":[31],"audio":[33],"and":[34,69,86,139],"features":[36],"concatenation,":[38],"without":[39],"explicit":[40],"interactions":[41],"to":[42,96,112],"capture":[43,97],"deep":[45,79],"correlations":[46,82,127],"between":[47],"them,":[48],"which":[49,76],"results":[50],"in":[51],"sub-optimal":[52],"multimodal":[53,130],"representations":[54,131],"for":[55,74,132],"downstream":[56],"task.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,90],"propose":[64],"cross-modal":[66,126],"global":[67,85,93],"interaction":[68,94],"local":[70,87,109],"alignment":[71,110],"(GILA)":[72],"approach":[73,111],"AVSR,":[75],"captures":[77],"audio-visual":[80],"(A-V)":[81],"from":[83],"both":[84],"perspectives.":[88],"Specifically,":[89],"design":[91],"model":[95,113],"A-V":[99,115],"complementary":[100],"relationship":[101],"on":[102,118,135],"modality":[103],"level,":[104],"as":[105,107],"well":[106],"temporal":[116],"consistency":[117],"frame":[119],"level.":[120],"Such":[121],"holistic":[123],"view":[124],"enable":[128],"better":[129],"AVSR.":[133],"Experiments":[134],"public":[136],"benchmarks":[137],"LRS3":[138],"LRS2":[140],"show":[141],"that":[142],"our":[143],"GILA":[144],"outperforms":[145],"supervised":[147],"learning":[148],"state-of-the-art.":[149],"Code":[150],"is":[151],"at":[152],"https://github.com/YUCHEN005/GILA.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}
