{"id":"https://openalex.org/W4372259972","doi":"https://doi.org/10.1109/icassp49357.2023.10095029","title":"Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation","display_name":"Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259972","doi":"https://doi.org/10.1109/icassp49357.2023.10095029"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100688790","display_name":"Jingxuan Zhang","orcid":"https://orcid.org/0000-0002-1655-6121"},"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"]},{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-Xuan Zhang","raw_affiliation_strings":["University of Science and Technology of China,China","iFLYTEK Research, iFLYTEK Co. Ltd., China","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"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"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"]},{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"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":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,China","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"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co. Ltd.,China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd.,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730084","display_name":"Jianqing Gao","orcid":"https://orcid.org/0000-0003-1052-7060"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co. Ltd.,China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd.,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331605","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0002-5999-2126"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co. Ltd.,China","iFLYTEK Research, iFLYTEK Co. Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd.,China","institution_ids":["https://openalex.org/I173632517"]},{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd., China","institution_ids":["https://openalex.org/I173632517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9980000257492065,"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":0.9968000054359436,"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":0.7744894027709961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6610597372055054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500360131263733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5320015549659729},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5277536511421204},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5191651582717896},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5177599787712097},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5020151138305664},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49183058738708496},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4650607705116272},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37527820467948914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744894027709961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6610597372055054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500360131263733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5320015549659729},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5277536511421204},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5191651582717896},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5177599787712097},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5020151138305664},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49183058738708496},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4650607705116272},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37527820467948914},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W2015394094","https://openalex.org/W2016165338","https://openalex.org/W2219249508","https://openalex.org/W2267805933","https://openalex.org/W2502312327","https://openalex.org/W2596627958","https://openalex.org/W2890052321","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2953070460","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2973049979","https://openalex.org/W2990408345","https://openalex.org/W3005680577","https://openalex.org/W3006974783","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3159481202","https://openalex.org/W3162293946","https://openalex.org/W3170863103","https://openalex.org/W3174954176","https://openalex.org/W3198098585","https://openalex.org/W3209059054","https://openalex.org/W3209483675","https://openalex.org/W4221145109","https://openalex.org/W4221153068","https://openalex.org/W4281892454","https://openalex.org/W4297841641","https://openalex.org/W4313156423","https://openalex.org/W6688816777","https://openalex.org/W6724804524","https://openalex.org/W6733814495","https://openalex.org/W6754048563","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6770805772","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6796069507","https://openalex.org/W6796761347","https://openalex.org/W6803344029","https://openalex.org/W6810007534","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W3165067022","https://openalex.org/W4320086214","https://openalex.org/W4298326888","https://openalex.org/W3132383226","https://openalex.org/W4287329508"],"abstract_inverted_index":{"In":[0],"this":[1,91],"work,":[2],"we":[3],"present":[4],"a":[5,20,23,31,54,97],"novel":[6],"method,":[7],"named":[8],"AV2vec,":[9],"for":[10],"learning":[11],"audio-visual":[12],"speech":[13],"representations":[14],"by":[15,44],"multimodal":[16,39],"self-distillation.":[17],"AV2vec":[18,67,95,111],"has":[19],"student":[21,29],"and":[22,74,128],"teacher":[24,51],"module,":[25],"in":[26,90],"which":[27,93],"the":[28,38,45,50,58,75,116,130,134],"performs":[30],"masked":[32,98],"latent":[33],"feature":[34],"regression":[35],"task":[36],"using":[37,103],"target":[40,62],"features":[41,63],"generated":[42,65],"online":[43],"teacher.":[46],"The":[47],"parameters":[48],"of":[49,57],"model":[52,100],"are":[53,64],"momentum":[55],"update":[56],"student.":[59],"Since":[60],"our":[61],"online,":[66],"needs":[68],"no":[69],"iteration":[70],"step":[71],"like":[72],"AV-HuBERT":[73,117],"total":[76],"training":[77],"time":[78],"cost":[79],"is":[80],"reduced":[81],"to":[82,115],"less":[83],"than":[84],"one-fifth.":[85],"We":[86],"further":[87],"propose":[88],"AV2vec-MLM":[89,125],"study,":[92],"augments":[94],"with":[96,121],"language":[99],"(MLM)-style":[101],"loss":[102],"multitask":[104],"learning.":[105],"Our":[106],"experimental":[107],"results":[108],"show":[109],"that":[110],"achieved":[112,129],"comparable":[113],"performance":[114,132],"baseline.":[118],"When":[119],"combined":[120],"an":[122],"MLM-style":[123],"loss,":[124],"outperformed":[126],"baselines":[127],"best":[131],"on":[133],"downstream":[135],"tasks.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
