{"id":"https://openalex.org/W4406859923","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848943","title":"Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions","display_name":"Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859923","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848943"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5103221904","display_name":"Jinyi Mi","orcid":"https://orcid.org/0009-0005-6560-4117"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinyi Mi","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101796991","display_name":"Xiaohan Shi","orcid":"https://orcid.org/0000-0002-1917-4479"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaohan Shi","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108239903","display_name":"Ding Ma","orcid":"https://orcid.org/0009-0008-2360-2035"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ding Ma","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601603","display_name":"Jiajun He","orcid":"https://orcid.org/0000-0002-2788-2440"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiajun He","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048172594","display_name":"Takuya Fujimura","orcid":"https://orcid.org/0000-0003-1726-8372"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Fujimura","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75949971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9775000214576721,"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":0.9775000214576721,"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":0.9660999774932861,"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/speech-recognition","display_name":"Speech recognition","score":0.8148033618927002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7383344173431396},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6464671492576599},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5453627705574036},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48613688349723816},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47432941198349},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4282044470310211},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42779913544654846},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.42210307717323303},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41751593351364136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3505384027957916},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18373945355415344}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8148033618927002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383344173431396},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6464671492576599},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5453627705574036},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48613688349723816},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47432941198349},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4282044470310211},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42779913544654846},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.42210307717323303},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41751593351364136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3505384027957916},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18373945355415344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4300000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2019977029","https://openalex.org/W2026799997","https://openalex.org/W2060079959","https://openalex.org/W2082492120","https://openalex.org/W2134707158","https://openalex.org/W2146334809","https://openalex.org/W2147634797","https://openalex.org/W2509597859","https://openalex.org/W2803098682","https://openalex.org/W2951130829","https://openalex.org/W2964058413","https://openalex.org/W3015636705","https://openalex.org/W3037246750","https://openalex.org/W3162475537","https://openalex.org/W4205742757","https://openalex.org/W4221162872","https://openalex.org/W4312768311","https://openalex.org/W4321609205","https://openalex.org/W4372341110","https://openalex.org/W4375869379","https://openalex.org/W4385823310","https://openalex.org/W6605703937","https://openalex.org/W6639288896","https://openalex.org/W6777776875","https://openalex.org/W6858207737"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Developing":[0],"a":[1,42,61,72,90,106,115],"robust":[2],"speech":[3,28,67,83,133],"emotion":[4],"recognition":[5],"(SER)":[6],"system":[7,104],"in":[8,75,98,109,127,149],"noisy":[9],"conditions":[10],"faces":[11],"challenges":[12],"posed":[13],"by":[14,49],"different":[15],"noise":[16],"properties.":[17],"Most":[18],"previous":[19],"studies":[20],"have":[21],"not":[22],"considered":[23],"the":[24,32,47,66,76,81,99,122,129],"impact":[25,130],"of":[26,35,68,93,124,131],"human":[27,132],"noise,":[29],"thus":[30],"limiting":[31],"application":[33],"scope":[34],"SER.":[36,57],"In":[37],"this":[38],"paper,":[39],"we":[40,79,88,136],"propose":[41],"novel":[43],"two-stage":[44],"framework":[45,126,145],"for":[46,84],"problem":[48],"cascading":[50],"target":[51,69],"speaker":[52,70,140],"extraction":[53],"(TSE)":[54],"method":[55],"and":[56,95],"We":[58],"first":[59],"train":[60],"TSE":[62,94,119],"model":[63],"to":[64,114],"extract":[65],"from":[71],"mixture.":[73,151],"Then,":[74],"second":[77,100],"stage,":[78],"utilize":[80],"extracted":[82],"SER":[85,96],"training.":[86],"Additionally,":[87],"explore":[89],"joint":[91],"training":[92],"models":[97],"stage.":[101],"Our":[102],"developed":[103],"achieves":[105],"14.33%":[107],"improvement":[108],"unweighted":[110],"accuracy":[111],"(UA)":[112],"compared":[113],"baseline":[116],"without":[117],"using":[118],"method,":[120],"demonstrating":[121],"effectiveness":[123],"our":[125,144],"mitigating":[128],"noise.":[134],"Moreover,":[135],"conduct":[137],"experiments":[138],"considering":[139],"gender,":[141],"showing":[142],"that":[143],"performs":[146],"particularly":[147],"well":[148],"different-gender":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}