{"id":"https://openalex.org/W4415708143","doi":"https://doi.org/10.1109/icme59968.2025.11209516","title":"MAMF-Net: Modality-Adaptive Masked Fusion Network for Speech Emotion Recognition","display_name":"MAMF-Net: Modality-Adaptive Masked Fusion Network for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708143","doi":"https://doi.org/10.1109/icme59968.2025.11209516"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5086705260","display_name":"Hengrui Li","orcid":"https://orcid.org/0009-0005-0960-3638"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengrui Li","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031010852","display_name":"Tianyi Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Lu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603879","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0002-6996-4081"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Taiyuan University of Technology,School of Software,Taiyuan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiyuan University of Technology,School of Software,Taiyuan,China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037390993","display_name":"Xiaopei Chen","orcid":"https://orcid.org/0000-0001-9064-3568"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopei Chen","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023276675","display_name":"Yongbing Zhang","orcid":"https://orcid.org/0000-0003-3320-2904"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbing Zhang","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445780","display_name":"Shaohui Liu","orcid":"https://orcid.org/0000-0002-1810-5412"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Liu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26661367,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9891999959945679,"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":0.9891999959945679,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002099999925121665,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.748199999332428},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6193000078201294},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.529699981212616},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5234000086784363},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4997999966144562},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.44519999623298645},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.42480000853538513},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4244000017642975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763000130653381},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.748199999332428},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6193000078201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":21,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2191779130","https://openalex.org/W2883409523","https://openalex.org/W2998356391","https://openalex.org/W3041561163","https://openalex.org/W3093051361","https://openalex.org/W3128412859","https://openalex.org/W3200104365","https://openalex.org/W3214432797","https://openalex.org/W4206326349","https://openalex.org/W4225776299","https://openalex.org/W4313156423","https://openalex.org/W4385573848","https://openalex.org/W4386068662","https://openalex.org/W4386075721","https://openalex.org/W4386482802","https://openalex.org/W4387967914","https://openalex.org/W4389523777","https://openalex.org/W4389752793","https://openalex.org/W4392172995","https://openalex.org/W4401042765"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,67],"novel":[4],"multimodal":[5,113],"emotion":[6,114],"recognition":[7],"model,":[8],"the":[9,25,40,47,64],"Modality-Adaptive":[10],"Masked":[11],"Fusion":[12],"Network":[13],"(MAMF-Net),":[14],"designed":[15],"to":[16,38],"mitigate":[17],"information":[18,52,77],"loss":[19],"and":[20,29,50,89,106],"improve":[21],"cross-modal":[22],"alignment":[23,59],"during":[24],"fusion":[26,87],"of":[27,43,60],"speech":[28],"text":[30,36,44],"modalities.":[31],"MAMF-Net":[32,97],"employs":[33],"an":[34],"audio-guided":[35],"encoder":[37],"enhance":[39],"semantic":[41],"representation":[42],"by":[45,80],"leveraging":[46],"temporal":[48],"resolution":[49],"contextual":[51],"inherent":[53],"in":[54],"speech,":[55],"thereby":[56],"ensuring":[57],"accurate":[58],"modal":[61],"features.":[62],"Additionally,":[63],"model":[65],"utilizes":[66],"modality":[68],"transfer-based":[69],"MAE":[70],"masking":[71,82],"strategy,":[72],"which":[73],"effectively":[74],"captures":[75],"complementary":[76],"between":[78],"modalities":[79],"partially":[81],"transferred":[83],"information,":[84],"thus":[85],"improving":[86],"effectiveness":[88],"system":[90],"stability.":[91],"The":[92],"experimental":[93],"results":[94],"show":[95],"that":[96],"outperforms":[98],"existing":[99],"methods":[100],"on":[101],"datasets":[102],"such":[103],"as":[104],"CMU-MOSI":[105],"CMU-MOSEI,":[107],"highlighting":[108],"its":[109],"significant":[110],"potential":[111],"for":[112],"analysis.":[115]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}