{"id":"https://openalex.org/W4392903409","doi":"https://doi.org/10.1109/icassp48485.2024.10448106","title":"LCB-Net: Long-Context Biasing for Audio-Visual Speech Recognition","display_name":"LCB-Net: Long-Context Biasing for Audio-Visual Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903409","doi":"https://doi.org/10.1109/icassp48485.2024.10448106"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448106","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/A5062644421","display_name":"Xian Shi","orcid":"https://orcid.org/0000-0002-4120-7361"},"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":"Xian Shi","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":1.7276,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83638098,"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":"10621","last_page":"10625"},"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":0.9997000098228455,"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":0.7654005885124207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.65371173620224},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4906074106693268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46772444248199463},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.45111727714538574},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44687962532043457},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4314831495285034},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4227573573589325},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3249675929546356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654005885124207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.65371173620224},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4906074106693268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46772444248199463},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.45111727714538574},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44687962532043457},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4314831495285034},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4227573573589325},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3249675929546356},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448106","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2896457183","https://openalex.org/W2903250132","https://openalex.org/W2936774411","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3097777922","https://openalex.org/W3160413945","https://openalex.org/W3198004110","https://openalex.org/W4225289150","https://openalex.org/W4225985539","https://openalex.org/W4300655590","https://openalex.org/W4385245566","https://openalex.org/W4385822246","https://openalex.org/W4385822684","https://openalex.org/W4392909790","https://openalex.org/W6638931011"],"related_works":["https://openalex.org/W2039546652","https://openalex.org/W2012262991","https://openalex.org/W2373794620","https://openalex.org/W2060629350","https://openalex.org/W2357294589","https://openalex.org/W4390516098","https://openalex.org/W2386861027","https://openalex.org/W2349302580","https://openalex.org/W2181948922","https://openalex.org/W2390154576"],"abstract_inverted_index":{"The":[0],"growing":[1],"prevalence":[2],"of":[3,45,123],"online":[4],"conferences":[5],"and":[6,82,121,158],"courses":[7],"presents":[8],"a":[9,52,75,89,112,130],"new":[10],"challenge":[11],"in":[12,37,69,105],"improving":[13],"automatic":[14],"speech":[15,60],"recognition":[16,61],"(ASR)":[17],"with":[18,39,135],"enriched":[19,134],"textual":[20],"information":[21,67],"from":[22],"video":[23],"slides.":[24],"In":[25],"contrast":[26],"to":[27,63,78,100,117,171],"rare":[28],"phrase":[29],"lists,":[30],"the":[31,40,43,65,106,119,128,177],"slides":[32],"within":[33],"videos":[34,70],"are":[35],"synchronized":[36],"real-time":[38],"speech,":[41],"enabling":[42],"extraction":[44],"long":[46],"contextual":[47,114],"bias.":[48],"Therefore,":[49],"we":[50,73,86,110,162],"propose":[51,88],"novel":[53],"long-context":[54,66,83,107],"biasing":[55,90],"network":[56],"(LCB-net)":[57],"for":[58],"audio-visual":[59,132],"(AVSR)":[62],"leverage":[64],"available":[68],"effectively.":[71],"Specifically,":[72],"adopt":[74],"bi-encoder":[76],"architecture":[77],"simultaneously":[79],"model":[80,145,166],"audio":[81],"biasing.":[84,108],"Besides,":[85],"also":[87,163],"prediction":[91],"module":[92],"that":[93,138],"utilizes":[94],"binary":[95],"cross":[96],"entropy":[97],"(BCE)":[98],"loss":[99],"explicitly":[101],"determine":[102],"biased":[103,159],"phrases":[104,115],"Furthermore,":[109],"introduce":[111],"dynamic":[113],"simulation":[116],"enhance":[118],"generalization":[120],"robustness":[122],"our":[124,139,165],"LCB-net.":[125],"Experiments":[126],"on":[127,151,167],"SlideSpeech,":[129],"large-scale":[131],"corpus":[133],"slides,":[136],"reveal":[137],"proposed":[140],"LCB-net":[141],"outperforms":[142],"general":[143],"ASR":[144,178],"by":[146],"9.4%/9.1%/10.9%":[147],"relative":[148,173],"WER/U-WER/B-WER":[149,174],"reduction":[150,175],"test":[152],"set,":[153],"which":[154],"enjoys":[155],"high":[156],"unbiased":[157],"performance.":[160],"Moreover,":[161],"evaluate":[164],"LibriSpeech":[168],"corpus,":[169],"leading":[170],"23.8%/19.2%/35.4%":[172],"over":[176],"model.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
