{"id":"https://openalex.org/W4224932149","doi":"https://doi.org/10.1109/icassp43922.2022.9746403","title":"An Audio-Saliency Masking Transformer for Audio Emotion Classification in Movies","display_name":"An Audio-Saliency Masking Transformer for Audio Emotion Classification in Movies","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932149","doi":"https://doi.org/10.1109/icassp43922.2022.9746403"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746403","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5072913376","display_name":"Ya-Tse Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ya-Tse Wu","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Taiwan","Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001894880","display_name":"Jeng-Lin Li","orcid":"https://orcid.org/0000-0002-9261-1524"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeng-Lin Li","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Taiwan","Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Taiwan","Department of Electrical Engineering, National Tsing Hua University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.242,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34812716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4813","last_page":"4817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.7175991535186768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6022005081176758},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5221543312072754},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4857237935066223},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4803091883659363},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.4668619632720947},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4274216890335083},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.42367273569107056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39286261796951294},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1751413345336914},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08782589435577393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175991535186768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6022005081176758},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5221543312072754},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4857237935066223},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4803091883659363},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.4668619632720947},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4274216890335083},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.42367273569107056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39286261796951294},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1751413345336914},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08782589435577393},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746403","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1589138511","https://openalex.org/W1992724000","https://openalex.org/W2006407148","https://openalex.org/W2026012689","https://openalex.org/W2090777335","https://openalex.org/W2121407761","https://openalex.org/W2156047020","https://openalex.org/W2156232986","https://openalex.org/W2404368331","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2742409927","https://openalex.org/W2763782214","https://openalex.org/W2808415943","https://openalex.org/W2883439561","https://openalex.org/W2889239910","https://openalex.org/W2912650733","https://openalex.org/W2928639725","https://openalex.org/W2972498864","https://openalex.org/W2973134256","https://openalex.org/W3160168209","https://openalex.org/W6635392147","https://openalex.org/W6784458999"],"related_works":["https://openalex.org/W2029072726","https://openalex.org/W91913183","https://openalex.org/W2936882366","https://openalex.org/W2736893848","https://openalex.org/W2128698257","https://openalex.org/W1544055438","https://openalex.org/W3003450285","https://openalex.org/W2013608943","https://openalex.org/W4399628019","https://openalex.org/W2085024878"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,7,72,107,117],"perception":[3],"to":[4,29,32,75,114,144],"affective":[5],"response":[6],"humans":[8],"is":[9,84],"gated":[10],"by":[11,42],"a":[12],"bottom-up":[13],"saliency":[14,23,78,141],"mechanism":[15],"at":[16],"the":[17,81,95,98,115,118,145],"sensory":[18],"level.":[19],"In":[20,38],"specifics,":[21],"auditory":[22,77],"emphasizes":[24],"audio":[25,53],"segments":[26],"that":[27,139],"need":[28],"be":[30],"attended":[31],"cognitively":[33],"appraise":[34],"and":[35,80,94,128],"experience":[36],"emotion.":[37],"this":[39,43],"work,":[40],"inspired":[41],"mechanism,":[44],"we":[45,102],"propose":[46],"an":[47,76],"end-to-end":[48],"feature":[49,65,137],"masking":[50],"network":[51],"for":[52,90],"emotion":[54,100],"recognition":[55],"in":[56],"movies.":[57],"Our":[58],"proposed":[59],"Audio-Saliency":[60],"Masking":[61],"Transformer":[62],"(ASTM)":[63],"adjusts":[64],"embedding":[66],"using":[67],"two":[68],"learnable":[69],"masks;":[70],"one":[71,83],"them":[73],"cross-refers":[74],"map,":[79],"other":[82,119],"through":[85],"self-reference.":[86],"By":[87],"joint":[88],"training":[89],"front-end":[91],"mask":[92,142],"gating":[93],"transformer":[96],"as":[97],"back-end":[99],"classifier,":[101],"achieve":[103],"three-class":[104],"UARs":[105],"improvement":[106],"1.74%,":[108],"1.27%,":[109],"0.95%,":[110],"0.82%":[111],"when":[112],"comparing":[113],"best":[116],"models":[120],"on":[121],"experienced":[122,124],"arousal,":[123,127],"valence,":[125,130],"intended":[126,129],"respectively.":[131],"We":[132],"further":[133],"analyze":[134],"which":[135],"acoustic":[136],"categories":[138],"our":[140],"attends":[143],"most.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}