{"id":"https://openalex.org/W4281635716","doi":"https://doi.org/10.1145/3529466.3529488","title":"Speech Emotion Recognition Exploiting ASR-based and Phonological Knowledge Representations","display_name":"Speech Emotion Recognition Exploiting ASR-based and Phonological Knowledge Representations","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4281635716","doi":"https://doi.org/10.1145/3529466.3529488"},"language":"en","primary_location":{"id":"doi:10.1145/3529466.3529488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529466.3529488","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 6th International Conference on Innovation in Artificial Intelligence (ICIAI)","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/A5057725829","display_name":"Shuang Liang","orcid":"https://orcid.org/0009-0005-8849-4432"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuang Liang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642396","display_name":"Xiang Xie","orcid":"https://orcid.org/0000-0002-6895-3145"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xie","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China, China and Shenzhen Research Institute, Beijing Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China, China and Shenzhen Research Institute, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065786740","display_name":"Qingran Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingran Zhan","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102482167","display_name":"Hao Cheng","orcid":"https://orcid.org/0009-0005-3476-2382"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Cheng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057725829"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04725811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9986000061035156,"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":0.8020790815353394},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.639965295791626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6141718626022339},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5380785465240479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328073501586914},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.52752286195755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5009503364562988},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4606170356273651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020790815353394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.639965295791626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6141718626022339},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5380785465240479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328073501586914},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.52752286195755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5009503364562988},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4606170356273651},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3529466.3529488","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529466.3529488","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 the 6th International Conference on Innovation in Artificial Intelligence (ICIAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067093722","https://openalex.org/W2889169802","https://openalex.org/W2937584914","https://openalex.org/W2972498864","https://openalex.org/W3094805191","https://openalex.org/W3096147072","https://openalex.org/W3096784008","https://openalex.org/W3201071655","https://openalex.org/W4200231323","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W3201126466","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2,37],"(SER)":[3],"is":[4,70,113,121,132,144],"a":[5,108,116],"challenging":[6],"problem":[7,18],"due":[8],"to":[9],"the":[10,41,67,99,124,135,155],"insufficient":[11],"dataset.":[12],"This":[13],"paper":[14],"deals":[15],"with":[16,85],"this":[17],"from":[19,57,95],"two":[20,25,73],"aspects.":[21],"First,":[22],"we":[23,48],"exploit":[24],"levels":[26],"of":[27],"speech":[28,36],"representations":[29,39,90],"for":[30,34,43,61,123,134,146],"SER":[31,79,105,136],"task,":[32,137],"one":[33],"automatic":[35],"(ASR)-based":[38],"and":[40,54,78,87,98,138,163],"other":[42,58],"phonological":[44,88,125],"knowledge":[45,56,89,126],"representations.":[46],"Second,":[47],"use":[49],"transfer":[50,55],"learning,":[51],"pre-train":[52],"models":[53],"large":[59],"corpus":[60],"none-SER":[62],"task.":[63],"In":[64],"our":[65,139],"system,":[66],"whole":[68],"model":[69,120],"divided":[71],"into":[72],"parts:":[74],"two-representation":[75],"learning":[76,111],"module":[77],"module.":[80],"We":[81],"fuse":[82],"acoustic":[83],"features":[84,101],"ASR-based":[86],"which":[91],"are":[92,102],"both":[93],"extracted":[94],"pre-trained":[96],"models,":[97],"fusion":[100],"used":[103,122],"in":[104],"training.":[106],"Then":[107],"novel":[109],"multi-task":[110],"approach":[112],"proposed":[114,156],"where":[115],"shared":[117],"encoder-multi":[118],"decoder":[119],"representation":[127],"learning.":[128],"The":[129],"Conformer":[130,143],"structure":[131],"introduced":[133],"study":[140],"indicates":[141],"that":[142,154],"effective":[145],"SER.":[147],"Finally,":[148],"experimental":[149],"results":[150],"on":[151],"IEMOCAP":[152],"show":[153],"method":[157],"can":[158],"achieve":[159],"77.35":[160],"weighted":[161],"accuracy":[162,166],"77.99":[164],"unweighted":[165],"respectively.":[167]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}