{"id":"https://openalex.org/W4405709212","doi":"https://doi.org/10.1109/iscslp63861.2024.10800480","title":"Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective","display_name":"Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709212","doi":"https://doi.org/10.1109/iscslp63861.2024.10800480"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100418433","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-3525-9755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Chen","raw_affiliation_strings":["BNRist, Tsinghua University,Center for Speech and Language Technologies"],"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Center for Speech and Language Technologies","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111228895","display_name":"Xiaolou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolou Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697560","display_name":"Zehua Liu","orcid":"https://orcid.org/0000-0003-0670-4300"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391452","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1964-3984"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["BNRist, Tsinghua University,Center for Speech and Language Technologies"],"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Center for Speech and Language Technologies","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100418433"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68437636,"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":"426","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.25459998846054077,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.25459998846054077,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/perspective","display_name":"Perspective (graphical)","score":0.7901785969734192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591023445129395},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7452361583709717},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49677973985671997},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4518621861934662},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.4378420412540436},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3680247962474823},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3173016905784607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28567156195640564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.28496313095092773},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.2044251561164856},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.13346442580223083},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11859685182571411}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7901785969734192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591023445129395},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7452361583709717},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49677973985671997},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4518621861934662},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.4378420412540436},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3680247962474823},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3173016905784607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28567156195640564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28496313095092773},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2044251561164856},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.13346442580223083},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11859685182571411}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6571611847","display_name":null,"funder_award_id":"62301075/62171250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1976968595","https://openalex.org/W1995875735","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2027665171","https://openalex.org/W2116873850","https://openalex.org/W2551572271","https://openalex.org/W2890952074","https://openalex.org/W2981087920","https://openalex.org/W3096831136","https://openalex.org/W3197659778","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W4206319965","https://openalex.org/W4221164771","https://openalex.org/W4289665794","https://openalex.org/W4296069328","https://openalex.org/W4297841641","https://openalex.org/W4327661848","https://openalex.org/W4372346152","https://openalex.org/W4375869161","https://openalex.org/W4392908934","https://openalex.org/W4392908956","https://openalex.org/W4392910805","https://openalex.org/W4402111743","https://openalex.org/W6640963894","https://openalex.org/W6732872814","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2362367986","https://openalex.org/W348707231","https://openalex.org/W2571228289","https://openalex.org/W4390204044","https://openalex.org/W4293108519","https://openalex.org/W3041760129","https://openalex.org/W4402262758","https://openalex.org/W3096250625","https://openalex.org/W3011716530","https://openalex.org/W4308222513"],"abstract_inverted_index":{"In":[0],"the":[1,73,82],"field":[2],"of":[3,17,75],"spoken":[4],"language":[5],"processing,":[6],"audio-visual":[7,26,44,76],"speech":[8,27],"processing":[9,77],"is":[10,40,69],"receiving":[11],"increasing":[12],"research":[13,19],"attention.":[14],"Key":[15],"components":[16],"this":[18,67],"include":[20],"tasks":[21,78],"such":[22],"as":[23,79,81],"lip":[24],"reading,":[25],"recognition,":[28],"and":[29],"visual-to-speech":[30],"synthesis.":[31],"Although":[32],"significant":[33],"success":[34],"has":[35],"been":[36],"achieved,":[37],"theoretical":[38],"analysis":[39,51,68],"still":[41],"insufficient":[42],"for":[43,71],"tasks.":[45],"This":[46],"paper":[47],"presents":[48],"a":[49],"quantitative":[50],"based":[52],"on":[53,57],"information":[54,58],"theory,":[55],"focusing":[56],"intersection":[59],"between":[60],"different":[61],"modalities.":[62],"Our":[63],"results":[64],"show":[65],"that":[66,84],"valuable":[70],"understanding":[72],"difficulties":[74],"well":[80],"benefits":[83],"could":[85],"be":[86],"obtained":[87],"by":[88],"modality":[89],"integration.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}