{"id":"https://openalex.org/W4406610976","doi":"https://doi.org/10.1109/taffc.2025.3531638","title":"Spectro-Temporal Modulations Incorporated Two-Stream Robust Speech Emotion Recognition","display_name":"Spectro-Temporal Modulations Incorporated Two-Stream Robust Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-01-20","ids":{"openalex":"https://openalex.org/W4406610976","doi":"https://doi.org/10.1109/taffc.2025.3531638"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3531638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3531638","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-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/A5063025053","display_name":"Yih-Liang Shen","orcid":"https://orcid.org/0000-0003-4789-6695"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yih-Liang Shen","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4789-6695","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pei-Chin Hsieh","orcid":"https://orcid.org/0009-0000-0720-3941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Chin Hsieh","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0000-0720-3941","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088864528","display_name":"Tai-Shih Chi","orcid":"https://orcid.org/0000-0002-0584-8399"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Shih Chi","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0584-8399","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2561,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93058152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1693","last_page":"1704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9448999762535095,"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/T10860","display_name":"Speech and Audio Processing","score":0.9448999762535095,"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/emotion-recognition","display_name":"Emotion recognition","score":0.6997759938240051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466240882873535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5187923312187195},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.43603450059890747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32499125599861145}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6997759938240051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466240882873535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5187923312187195},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.43603450059890747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32499125599861145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3531638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3531638","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5299011973","display_name":null,"funder_award_id":"MOST 110-2221-E-A49-115-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1844030040","https://openalex.org/W1907246751","https://openalex.org/W1963552095","https://openalex.org/W1993393712","https://openalex.org/W2000838212","https://openalex.org/W2011114978","https://openalex.org/W2017996716","https://openalex.org/W2041202046","https://openalex.org/W2054139811","https://openalex.org/W2101724615","https://openalex.org/W2126617887","https://openalex.org/W2183341477","https://openalex.org/W2243226955","https://openalex.org/W2295001676","https://openalex.org/W2516665493","https://openalex.org/W2625297138","https://openalex.org/W2785960144","https://openalex.org/W2803193013","https://openalex.org/W2883496341","https://openalex.org/W2885005742","https://openalex.org/W2889530575","https://openalex.org/W2896939631","https://openalex.org/W2936372954","https://openalex.org/W2971275122","https://openalex.org/W2972614117","https://openalex.org/W2972852081","https://openalex.org/W2980520956","https://openalex.org/W3016617474","https://openalex.org/W3022013598","https://openalex.org/W3097341095","https://openalex.org/W3136524425","https://openalex.org/W3163091219","https://openalex.org/W3197078573","https://openalex.org/W3197156295","https://openalex.org/W4224436620","https://openalex.org/W4224933371","https://openalex.org/W4225635674","https://openalex.org/W4239447739","https://openalex.org/W4285144065","https://openalex.org/W4285235436","https://openalex.org/W4320068120","https://openalex.org/W4372269797","https://openalex.org/W4385822457","https://openalex.org/W4391129321","https://openalex.org/W4392904469","https://openalex.org/W4392908343"],"related_works":["https://openalex.org/W3080495370","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4285597148","https://openalex.org/W2901531394","https://openalex.org/W1559262936","https://openalex.org/W2134707158","https://openalex.org/W4321599321","https://openalex.org/W2767348466","https://openalex.org/W2141728578"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"speech":[3,102],"emotion":[4],"recognition":[5],"(SER)":[6],"models":[7],"have":[8],"shown":[9],"impressive":[10],"results":[11,55],"in":[12,20,64,104,133],"controlled":[13],"environments,":[14],"but":[15,123],"their":[16],"performance":[17],"significantly":[18],"degrades":[19],"noisy":[21,65],"conditions.":[22],"This":[23],"paper":[24],"proposes":[25],"a":[26],"robust":[27,107],"two-stream":[28],"SER":[29,132],"model":[30,90,122],"by":[31],"combining":[32],"spectro-temporal":[33,58,113],"modulation":[34,59,85],"features":[35,60,71,77,86,100],"with":[36,68],"conventional":[37,69],"acoustic":[38,70],"features.":[39],"Experiments":[40],"were":[41],"conducted":[42],"on":[43],"German":[44],"(EMODB)":[45],"and":[46,75,87,95],"English":[47],"(RAVDESS)":[48],"datasets":[49],"using":[50],"the":[51,89,110,118,121,129],"clean-train-noisy-test":[52],"paradigm.":[53],"The":[54],"demonstrate":[56,88],"that":[57],"offer":[61],"superior":[62],"robustness":[63,119],"conditions":[66],"compared":[67],"such":[72],"as":[73],"MFCCs":[74],"time-frequency":[76],"from":[78],"Mel-spectrograms.":[79],"Additionally,":[80],"we":[81],"analyze":[82],"weights":[83],"of":[84,93,112,120,131],"emphasizes":[91],"contours":[92],"formants":[94],"harmonics,":[96],"which":[97],"are":[98],"crucial":[99],"for":[101,106],"perception":[103],"noise,":[105],"SER.":[108],"Incorporating":[109],"stream":[111],"modulations":[114],"not":[115],"only":[116],"enhances":[117],"also":[124],"provides":[125],"deeper":[126],"insights":[127],"into":[128],"task":[130],"noise.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}