{"id":"https://openalex.org/W4392904414","doi":"https://doi.org/10.1109/icassp48485.2024.10448373","title":"A Robust Pitch-Fusion Model for Speech Emotion Recognition in Tonal Languages","display_name":"A Robust Pitch-Fusion Model for Speech Emotion Recognition in Tonal Languages","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904414","doi":"https://doi.org/10.1109/icassp48485.2024.10448373"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108296873","display_name":"Pham Viet Thanh","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham Viet Thanh","raw_affiliation_strings":["Hanoi University of Science and Technology,Vietnam","Hanoi University of Science and Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Hanoi University of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085398905","display_name":"Ngo Thi Thu Huyen","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngo Thi Thu Huyen","raw_affiliation_strings":["Hanoi University of Science and Technology,Vietnam","Hanoi University of Science and Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Hanoi University of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088407231","display_name":"Pham Ngoc Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham Ngoc Quan","raw_affiliation_strings":["Hanoi University of Science and Technology,Vietnam","Hanoi University of Science and Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Hanoi University of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101435787","display_name":"Nguy\u1ec5n Th\u1ecb Thu Trang","orcid":"https://orcid.org/0000-0002-5015-082X"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Thi Thu Trang","raw_affiliation_strings":["Hanoi University of Science and Technology,Vietnam","Hanoi University of Science and Technology, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Hanoi University of Science and Technology, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":5.8411,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9602621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12386","last_page":"12390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7686007618904114},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7254383563995361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6860973238945007},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6518521308898926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5401922464370728},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49097540974617004},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4788248836994171},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46757274866104126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42280739545822144},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41348108649253845},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13965708017349243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686007618904114},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7254383563995361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6860973238945007},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6518521308898926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5401922464370728},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49097540974617004},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4788248836994171},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46757274866104126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42280739545822144},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41348108649253845},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13965708017349243},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2085628288","https://openalex.org/W2146334809","https://openalex.org/W2969985801","https://openalex.org/W2972397073","https://openalex.org/W3007243649","https://openalex.org/W3034552680","https://openalex.org/W3081192838","https://openalex.org/W3119308075","https://openalex.org/W3196974791","https://openalex.org/W3203407300","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4385245566","https://openalex.org/W4385807464","https://openalex.org/W4385823030","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W2532164695","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"is":[4,24,141],"an":[5,109],"essential":[6],"task":[7],"in":[8,62,112],"spoken":[9],"language":[10],"processing,":[11],"applicable":[12],"across":[13],"various":[14],"domains.":[15],"While":[16],"research":[17],"on":[18,105,147],"SER":[19,46,56],"systems":[20],"for":[21,32,49,136],"English":[22],"datasets":[23],"growing":[25],"rapidly,":[26],"the":[27,82,122,131],"reliability":[28],"of":[29,124],"these":[30],"models":[31],"tonal":[33,50,55,106],"languages":[34],"remains":[35],"a":[36,44,67,87,156],"significant":[37],"concern.":[38],"Therefore,":[39],"this":[40],"paper":[41],"introduces":[42],"Pitch-fusion,":[43],"novel":[45],"model":[47,53,90,100],"tailored":[48],"languages.":[51],"This":[52,139],"enhances":[54],"performance":[57],"by":[58],"leveraging":[59],"pitch":[60,68,79],"features":[61,80,85,171],"speech":[63,88],"segments.":[64],"Pitch-fusion":[65],"integrates":[66],"encoder":[69],"module,":[70],"with":[71,81,149],"efficient":[72],"cross-attention":[73],"and":[74,151,168,170],"self-attention":[75],"mechanisms":[76],"to":[77,118],"align":[78],"contextual":[83],"acoustic":[84],"from":[86,116,143,174],"representation":[89],"like":[91],"Wav2Vec":[92,103],"2.0.":[93],"Experimental":[94],"results":[95],"reveal":[96],"that":[97],"our":[98],"proposed":[99,157],"consistently":[101],"outperforms":[102],"2.0":[104],"datasets,":[107,127],"giving":[108],"absolute":[110],"improvement":[111],"weighted":[113],"accuracy":[114],"ranging":[115],"9.53%":[117],"21.11%.":[119],"Furthermore,":[120],"addressing":[121],"lack":[123],"public":[125,144],"Vietnamese":[126,137,176],"we":[128],"introduce":[129],"ViSEC,":[130],"first":[132],"openly":[133],"available":[134],"resource":[135],"SER.":[138],"dataset":[140],"collected":[142],"media":[145],"focusing":[146],"sources":[148],"rich":[150],"balanced":[152],"emotional":[153,163],"content.":[154],"Through":[155],"construction":[158],"pipeline,":[159],"ViSEC":[160],"includes":[161],"four":[162],"categories:":[164],"angry,":[165],"sad,":[166],"neutral,":[167],"happy,":[169],"5,280":[172],"utterances":[173],"147":[175],"speakers.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
