{"id":"https://openalex.org/W2005398341","doi":"https://doi.org/10.1109/icassp.2013.6639174","title":"Emotional speaker recognition based on i-vector through Atom Aligned Sparse Representation","display_name":"Emotional speaker recognition based on i-vector through Atom Aligned Sparse Representation","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2005398341","doi":"https://doi.org/10.1109/icassp.2013.6639174","mag":"2005398341"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5100379287","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-8664-1276"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["College of Computer Science & Technology, Zhejiang University, Hangzhou, China","[College of Computer Science and Technology, Zhejiang University, HangZhou, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"[College of Computer Science and Technology, Zhejiang University, HangZhou, China]","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054835275","display_name":"Yingchun Yang","orcid":"https://orcid.org/0000-0002-5582-7836"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchun Yang","raw_affiliation_strings":["College of Computer Science & Technology, Zhejiang University, Hangzhou, China","[College of Computer Science and Technology, Zhejiang University, HangZhou, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science & Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"[College of Computer Science and Technology, Zhejiang University, HangZhou, China]","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7760","last_page":"7764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9912999868392944,"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":0.9912999868392944,"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":0.9907000064849854,"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/T10057","display_name":"Face and Expression Recognition","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6707736253738403},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6698089838027954},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.655349612236023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6466443538665771},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6289196610450745},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6034992337226868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5927913784980774},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5163637399673462},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4854353070259094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48082125186920166},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4404255449771881},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43162044882774353},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10701751708984375}],"concepts":[{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6707736253738403},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6698089838027954},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.655349612236023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6466443538665771},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6289196610450745},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6034992337226868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5927913784980774},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5163637399673462},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4854353070259094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48082125186920166},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4404255449771881},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43162044882774353},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10701751708984375},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W6227892","https://openalex.org/W120011775","https://openalex.org/W152668300","https://openalex.org/W1999348785","https://openalex.org/W2096479899","https://openalex.org/W2107638917","https://openalex.org/W2113606819","https://openalex.org/W2114421877","https://openalex.org/W2161710584","https://openalex.org/W2245139446","https://openalex.org/W6606286508","https://openalex.org/W6676903177","https://openalex.org/W6677471066"],"related_works":["https://openalex.org/W4234190324","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W4396668120","https://openalex.org/W66821593","https://openalex.org/W2126085626","https://openalex.org/W204267554","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076"],"abstract_inverted_index":{"I-vector":[0],"algorithm":[1,61,94,100],"was":[2],"previously":[3],"adopted":[4],"to":[5,69],"improve":[6],"the":[7,32,49,76,92,96,105],"performance":[8],"of":[9,51],"ASR":[10],"(Automatic":[11],"Speaker":[12],"Recognition)":[13],"system":[14],"which":[15,30],"is":[16,25,34,39,54,67],"degraded":[17],"by":[18],"emotion":[19,43,52,59,77],"variability.":[20],"The":[21,81],"variability":[22,33,44,53,78,98],"compensation":[23,99],"technique":[24],"LDA":[26],"(Linear":[27],"Discriminant":[28],"Analysis)":[29],"assumes":[31],"speaker-independent.":[35],"However,":[36],"this":[37,71],"assumption":[38],"not":[40],"suitable":[41],"for":[42],"because":[45],"we":[46],"discover":[47],"that":[48,87],"pattern":[50,73],"speaker-dependent.":[55],"Therefore,":[56],"a":[57],"novel":[58],"synthesis":[60],"AASR":[62],"(Atom":[63],"Aligned":[64],"Sparse":[65],"Representation)":[66],"proposed":[68],"characterize":[70],"speaker-dependent":[72],"and":[74,95,108],"compensate":[75],"within":[79],"i-vectors.":[80],"experiments":[82],"conducted":[83],"on":[84],"MASC":[85],"show":[86],"our":[88],"algorithm,":[89],"compared":[90],"with":[91],"GMM-UBM":[93],"conventional":[97],"LDA,":[101],"both":[102],"can":[103],"enhance":[104],"speaker":[106],"identification":[107],"verification":[109],"performances.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}