{"id":"https://openalex.org/W4417073398","doi":"https://doi.org/10.1145/3743093.3771046","title":"Speech Emotion Recognition via Multi-Level Acoustic Modeling and Cross-Modal Temporal Fusion","display_name":"Speech Emotion Recognition via Multi-Level Acoustic Modeling and Cross-Modal Temporal Fusion","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073398","doi":"https://doi.org/10.1145/3743093.3771046"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771046","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xuan Zhang","orcid":"https://orcid.org/0009-0004-1880-1604"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zhang","raw_affiliation_strings":["Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0004-1880-1604","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092026405","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-4851-2094"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-4851-2094","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106716389","display_name":"Jianqiang Zhang","orcid":"https://orcid.org/0009-0007-4670-2197"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Zhang","raw_affiliation_strings":["Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0007-4670-2197","affiliations":[{"raw_affiliation_string":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Industrial Network and Information System Security, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022814673","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-7624-1917"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0001-7624-1917","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106716608","display_name":"Fuqiang Wang","orcid":"https://orcid.org/0000-0003-2843-0136"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuqiang Wang","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0003-2843-0136","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072473143","display_name":"Xiaoming Wu","orcid":"https://orcid.org/0009-0004-3160-0620"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Wu","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0004-3160-0620","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36326561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9460999965667725,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9460999965667725,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.022199999541044235,"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":0.006800000090152025,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5746999979019165},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5562000274658203},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.51419997215271},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.505299985408783},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4740999937057495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3889000117778778},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.3824999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014000058174133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6969000101089478},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5562000274658203},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936999976634979},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3771046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3771046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3771046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3771046","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308724","display_name":"Texas Space Grant Consortium","ror":"https://ror.org/05k1jx057"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073398.pdf","grobid_xml":"https://content.openalex.org/works/W4417073398.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2146334809","https://openalex.org/W2399733683","https://openalex.org/W2742542661","https://openalex.org/W2972452068","https://openalex.org/W2973037561","https://openalex.org/W2973181312","https://openalex.org/W3095612572","https://openalex.org/W3096723250","https://openalex.org/W3160039712","https://openalex.org/W3163091219","https://openalex.org/W3164582967","https://openalex.org/W4221161909","https://openalex.org/W4221162872","https://openalex.org/W4372267458","https://openalex.org/W4388027396","https://openalex.org/W4389459413","https://openalex.org/W4391423077","https://openalex.org/W4406243501"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"aims":[4],"to":[5,8,88],"enable":[6],"machines":[7],"understand":[9],"human":[10],"affective":[11],"states":[12],"using":[13,76,173],"only":[14],"audio":[15],"signals.":[16],"However,":[17],"effectively":[18],"extracting":[19,158],"and":[20,56,116,149,154,171,182],"leveraging":[21],"comprehensive":[22],"acoustic":[23,37,107],"information":[24],"remains":[25],"a":[26,41,62,93,129,142],"challenging":[27],"task.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,59,102,125],"propose":[33],"an":[34,77],"end-to-end":[35],"multi-level":[36],"modeling":[38,146],"framework":[39],"with":[40],"newly":[42],"designed":[43],"Cross-Temporal":[44],"Affective":[45],"Fusion":[46],"(CTAF)":[47],"module":[48],"for":[49,135,145,157],"dimensional":[50],"emotion":[51],"prediction":[52],"(e.g.,":[53],"valence,":[54],"arousal":[55],"dominance).":[57],"Specifically,":[58],"first":[60],"apply":[61],"dynamic":[63,150],"chunk":[64],"segmentation":[65],"strategy,":[66],"where":[67],"each":[68,89,121],"speech":[69],"signal":[70],"is":[71,84],"divided":[72],"into":[73],"overlapping":[74],"chunks":[75],"adaptive":[78],"step":[79,82],"size.":[80],"The":[81,162],"size":[83],"automatically":[85],"adjusted":[86],"according":[87],"utterance\u2019s":[90],"length,":[91],"ensuring":[92],"fixed":[94],"number":[95],"of":[96,106],"equal-duration":[97],"chunks.":[98],"From":[99],"these":[100],"chunks,":[101],"extract":[103],"three":[104],"levels":[105],"features:":[108],"Low-Level":[109],"Descriptors":[110],"(LLDs),":[111],"Mel-Frequency":[112],"Cepstral":[113],"Coefficient":[114],"(MFCC),":[115],"WavLM":[117,156],"representations.":[118],"To":[119],"model":[120,188],"feature":[122],"type":[123],"effectively,":[124],"design":[126],"specialized":[127],"encoders:":[128],"Fusion-Aware":[130],"Temporal":[131],"Convolutional":[132],"Network":[133],"(FATCNet)":[134],"capturing":[136],"local":[137],"temporal":[138],"dynamics":[139],"in":[140,152],"LLDs,":[141],"CNN-LSTM":[143],"architecture":[144],"both":[147],"static":[148],"patterns":[151],"MFCCs,":[153],"the":[155,174,180],"global":[159],"contextual":[160],"semantics.":[161],"extracted":[163],"features":[164],"are":[165],"then":[166],"treated":[167],"as":[168],"multi-modal":[169],"inputs":[170],"fused":[172],"proposed":[175],"CTAF":[176],"module.":[177],"Experiments":[178],"on":[179],"MSP-Podcast":[181],"IEMOCAP":[183],"datasets":[184],"demonstrate":[185],"that":[186],"our":[187],"achieves":[189],"competitive":[190],"SER":[191],"performance.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-06T00:00:00"}