{"id":"https://openalex.org/W2935898178","doi":"https://doi.org/10.1109/icassp.2019.8683185","title":"Speaker Characterization Using TDNN-LSTM Based Speaker Embedding","display_name":"Speaker Characterization Using TDNN-LSTM Based Speaker Embedding","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2935898178","doi":"https://doi.org/10.1109/icassp.2019.8683185","mag":"2935898178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5087434278","display_name":"Chia-Ping Chen","orcid":"https://orcid.org/0000-0002-7022-3061"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ping Chen","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052787638","display_name":"Su-Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Su-Yu Zhang","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102214259","display_name":"Chih-Ting Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Ting Yeh","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052057343","display_name":"Tenghui Wang","orcid":"https://orcid.org/0000-0003-1605-4153"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tenghui Wang","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103086620","display_name":"Chien-Lin Huang","orcid":"https://orcid.org/0000-0003-3157-4173"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Lin Huang","raw_affiliation_strings":["National Sun Yat-Sen University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Sun Yat-Sen University, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3137,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91049428,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9976000189781189,"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/nist","display_name":"NIST","score":0.8070387840270996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806910276412964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6908866763114929},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6570092439651489},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6156672835350037},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5801750421524048},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5439935922622681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5161755681037903},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5142290592193604},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.49685314297676086},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4874463379383087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4730640649795532},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4668138027191162},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4105342626571655}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8070387840270996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806910276412964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6908866763114929},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6570092439651489},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6156672835350037},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5801750421524048},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5439935922622681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5161755681037903},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5142290592193604},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.49685314297676086},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4874463379383087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4730640649795532},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4668138027191162},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4105342626571655},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W175605219","https://openalex.org/W1524333225","https://openalex.org/W2039057510","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2398284433","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2587150483","https://openalex.org/W2594345168","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2807627734","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W4234330420","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6712930963","https://openalex.org/W6713762819"],"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/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"In":[0,96],"this":[1],"paper":[2],"we":[3],"propose":[4],"speaker":[5,19,34,67],"characterization":[6],"using":[7],"time":[8],"delay":[9],"neural":[10,16],"networks":[11,17],"and":[12,47,64,121],"long":[13],"short-term":[14],"memory":[15],"(TDNN-LSTM)":[18],"embedding.":[20,35],"Three":[21,36],"types":[22],"of":[23,38,49,62,83,107,119,127],"front-end":[24],"feature":[25],"extraction":[26],"are":[27,41,56],"investigated":[28],"to":[29,43],"find":[30],"good":[31],"features":[32],"for":[33],"kinds":[37],"data":[39],"augmentation":[40],"used":[42],"increase":[44],"the":[45,50,59,76,86,105,110,130],"amount":[46],"diversity":[48],"training":[51],"data.":[52],"The":[53],"proposed":[54,77,111],"methods":[55,78,112],"evaluated":[57],"with":[58,85,92,129],"National":[60],"Institute":[61],"Standards":[63],"Technology":[65],"(NIST)":[66],"recognition":[68],"evaluation":[69,133],"(SRE)":[70],"tasks.":[71],"Experimental":[72],"results":[73],"show":[74],"that":[75],"achieve":[79,113],"a":[80,93,122],"decision":[81,124],"cost":[82,125],"0.400":[84],"pooled":[87],"SRE":[88,131],"2018":[89],"development":[90],"set":[91],"single":[94],"system.":[95],"addition,":[97],"by":[98],"applying":[99],"simple":[100],"average":[101],"score":[102],"combination":[103],"on":[104],"outputs":[106],"12":[108],"systems,":[109],"an":[114],"equal":[115],"error":[116],"rate":[117],"(EER)":[118],"5.56%":[120],"minimum":[123],"function":[126],"0.423":[128],"2016":[132],"set.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}