{"id":"https://openalex.org/W3015584015","doi":"https://doi.org/10.1109/icassp40776.2020.9052918","title":"Spectrogram Analysis Via Self-Attention for Realizing Cross-Model Visual-Audio Generation","display_name":"Spectrogram Analysis Via Self-Attention for Realizing Cross-Model Visual-Audio Generation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015584015","doi":"https://doi.org/10.1109/icassp40776.2020.9052918","mag":"3015584015"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5056901332","display_name":"Huadong Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huadong Tan","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046659139","display_name":"Guang Wu","orcid":"https://orcid.org/0000-0001-9855-1561"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Wu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030474289","display_name":"Pengcheng Zhao","orcid":"https://orcid.org/0000-0003-3774-5113"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhao","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065366225","display_name":"Yanxiang Chen","orcid":"https://orcid.org/0000-0002-1163-7926"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiang Chen","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056901332"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65134957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4392","last_page":"4396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9925000071525574,"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/spectrogram","display_name":"Spectrogram","score":0.8858550190925598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8160485625267029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5761973261833191},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5532483458518982},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5494685173034668},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5288817882537842},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5119286775588989},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4641638398170471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4579213857650757},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.439432293176651},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4215611219406128},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2118617594242096}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8858550190925598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160485625267029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5761973261833191},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5532483458518982},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5494685173034668},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5288817882537842},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5119286775588989},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4641638398170471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4579213857650757},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.439432293176651},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4215611219406128},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2118617594242096},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1902237438","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2133564696","https://openalex.org/W2405756170","https://openalex.org/W2584992898","https://openalex.org/W2619697695","https://openalex.org/W2759171953","https://openalex.org/W2785678896","https://openalex.org/W2787579267","https://openalex.org/W2804078698","https://openalex.org/W2949999304","https://openalex.org/W2962699416","https://openalex.org/W2962754210","https://openalex.org/W2962865004","https://openalex.org/W2963066677","https://openalex.org/W2963403868","https://openalex.org/W2963663420","https://openalex.org/W2963836885","https://openalex.org/W2963966654","https://openalex.org/W2964308564","https://openalex.org/W2981851635","https://openalex.org/W2989980422","https://openalex.org/W3037695135","https://openalex.org/W3101943858","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6678815747","https://openalex.org/W6679434410","https://openalex.org/W6713645886","https://openalex.org/W6739901393","https://openalex.org/W6748582592","https://openalex.org/W6748655329","https://openalex.org/W6750599028","https://openalex.org/W6752378368","https://openalex.org/W6779841522"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Human":[0],"cognition":[1],"is":[2,65,77],"supported":[3],"by":[4],"the":[5,28,36,45,54,57,62,72,82,85,89,99,108,113,121],"combination":[6,55],"of":[7,13,30,38,56,84,88,93,117],"multimodal":[8],"information":[9],"from":[10,32,40],"different":[11],"sources":[12],"perception.":[14],"The":[15,103],"two":[16],"most":[17],"important":[18],"modalities":[19],"are":[20,95,127],"visual":[21],"and":[22,115],"audio.":[23],"Cross-modal":[24],"visual-audio":[25,69,132],"generation":[26,70,114],"enables":[27],"synthesis":[29],"data":[31,39],"one":[33],"modality":[34],"following":[35],"acquisition":[37],"another.":[41],"This":[42,75],"brings":[43],"about":[44],"full":[46],"experience":[47],"that":[48,107,126],"can":[49],"only":[50],"be":[51],"achieved":[52],"through":[53],"two.":[58],"In":[59],"this":[60],"paper,":[61],"Self-Attention":[63,109],"mechanism":[64],"applied":[66],"to":[67,79,97,129],"cross-modal":[68,131],"for":[71],"first":[73],"time.":[74],"technique":[76],"implemented":[78],"assist":[80],"in":[81],"analysis":[83],"structural":[86],"characteristics":[87],"spectrogram.":[90],"A":[91],"series":[92],"experiments":[94],"conducted":[96],"discover":[98],"best":[100],"performing":[101],"configuration.":[102],"post-experimental":[104],"comparison":[105],"shows":[106],"module":[110],"greatly":[111],"improves":[112],"classification":[116],"audio":[118],"data.":[119],"Furthermore,":[120],"presented":[122],"method":[123],"achieves":[124],"results":[125],"superior":[128],"existing":[130],"generative":[133],"models.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}