{"id":"https://openalex.org/W3011561567","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023103","title":"Speaker Embedding Extraction with Multi-feature Integration Structure","display_name":"Speaker Embedding Extraction with Multi-feature Integration Structure","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011561567","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023103","mag":"3011561567"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023103","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5100414996","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-3938-7033"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University,China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University,China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764009","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0002-9283-0209"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Lu","raw_affiliation_strings":["School of Information Science and Engineering, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021434500","display_name":"Jianfeng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhou","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University,China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University,China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University,China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University,China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["School of Information Science and Engineering, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100414996"],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68042673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"450","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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":0.9969000220298767,"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":0.7429174184799194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6566098928451538},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6140807867050171},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6060570478439331},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5540145635604858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008604526519775},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49514833092689514},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49003374576568604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46817082166671753},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4427240192890167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4381502866744995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3697250187397003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429174184799194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6566098928451538},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6140807867050171},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6060570478439331},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5540145635604858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008604526519775},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49514833092689514},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49003374576568604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46817082166671753},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4427240192890167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4381502866744995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3697250187397003},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023103","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":29,"referenced_works":["https://openalex.org/W128628490","https://openalex.org/W1006777433","https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2090861223","https://openalex.org/W2103075368","https://openalex.org/W2114925438","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2161483003","https://openalex.org/W2167768673","https://openalex.org/W2194775991","https://openalex.org/W2295634712","https://openalex.org/W2402146185","https://openalex.org/W2584329820","https://openalex.org/W2590129515","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2890964092","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W6605273041","https://openalex.org/W6631362777","https://openalex.org/W6697322189","https://openalex.org/W6712930963"],"related_works":["https://openalex.org/W3185645817","https://openalex.org/W2535632265","https://openalex.org/W2934520842","https://openalex.org/W3115366194","https://openalex.org/W2155671730","https://openalex.org/W2912658917","https://openalex.org/W187080131","https://openalex.org/W2888068624","https://openalex.org/W3131419525","https://openalex.org/W3020807334","https://openalex.org/W2155448389","https://openalex.org/W2535714000","https://openalex.org/W3163985801","https://openalex.org/W2021299849","https://openalex.org/W2079789993","https://openalex.org/W2939479117","https://openalex.org/W3019329687","https://openalex.org/W2541396094","https://openalex.org/W2914484336","https://openalex.org/W2168227095"],"abstract_inverted_index":{"Recently":[0],"x-vector":[1,29],"has":[2],"achieved":[3],"a":[4,33,103,134],"promising":[5],"performance":[6],"of":[7,14,43,70,83,92],"speaker":[8,44],"verification":[9],"task":[10],"and":[11,31,61,123],"becomes":[12],"one":[13,74,81],"the":[15,23,28,40,58,62,87,90,93,110,119,124,128,139],"mainstream":[16],"systems.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"analyzed":[22],"feature":[24,41],"engineering":[25],"based":[26],"on":[27,86,118],"structure,":[30],"proposed":[32,47,129],"multi-feature":[34,48,130],"integration":[35,49,131],"method":[36,50,132],"to":[37,66],"further":[38],"improve":[39],"representation":[42],"characteristic.":[45],"The":[46,114],"could":[51],"be":[52],"implemented":[53],"in":[54,73,141],"two":[55,94],"ways,":[56],"with":[57],"symmetric":[59],"branches":[60,95],"asymmetric":[63],"branches,":[64],"respectively,":[65],"incorporate":[67],"different":[68],"types":[69],"acoustic":[71,84],"features":[72,85],"neural":[75],"network.":[76],"While":[77],"each":[78,97],"branch":[79],"processed":[80],"type":[82],"frame":[88,98],"level,":[89],"outputs":[91],"for":[96],"were":[99,116],"spliced":[100],"together":[101],"as":[102],"super":[104],"vector":[105],"before":[106],"being":[107],"input":[108],"into":[109],"statistics":[111],"pooling":[112],"layer.":[113],"experiments":[115],"executed":[117],"VoxCeleb1":[120],"data":[121],"set,":[122],"results":[125],"showed":[126],"that":[127],"obtained":[133],"22.8%":[135],"relative":[136],"improvement":[137],"over":[138],"baseline":[140],"EER":[142],"value.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}