{"id":"https://openalex.org/W2964247977","doi":"https://doi.org/10.21437/interspeech.2018-1226","title":"Speaker Embedding Extraction with Phonetic Information","display_name":"Speaker Embedding Extraction with Phonetic Information","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2964247977","doi":"https://doi.org/10.21437/interspeech.2018-1226","mag":"2964247977"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","Tsinghua National Laboratory for Information Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology,","Department of Electronic Engineering, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology,","institution_ids":[]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology,","Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","Department of Electrical and Computer Engineering, University of Kentucky 453 F. Paul Anderson Tower, Lexington, KY 40506-0046, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology,","institution_ids":[]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Kentucky 453 F. Paul Anderson Tower, Lexington, KY 40506-0046, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2247","last_page":"2251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9911999702453613,"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":0.9836000204086304,"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":0.7813997268676758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6835721135139465},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5753876566886902},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4909132122993469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4607831537723541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43827754259109497},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42468971014022827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813997268676758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6835721135139465},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5753876566886902},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4909132122993469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4607831537723541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43827754259109497},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42468971014022827}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2201735945","display_name":null,"funder_award_id":"61273268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2571867183","display_name":null,"funder_award_id":"61370034","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4665116016","display_name":null,"funder_award_id":"61403224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W119864726","https://openalex.org/W123007118","https://openalex.org/W204053250","https://openalex.org/W1524333225","https://openalex.org/W1985371235","https://openalex.org/W2002342963","https://openalex.org/W2046056978","https://openalex.org/W2072254246","https://openalex.org/W2079623482","https://openalex.org/W2150769028","https://openalex.org/W2289985966","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2402935018","https://openalex.org/W2406778302","https://openalex.org/W2565624985","https://openalex.org/W2566925314","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2786149683","https://openalex.org/W2950051476","https://openalex.org/W2962788625","https://openalex.org/W2962832278","https://openalex.org/W4299812321"],"related_works":["https://openalex.org/W4365793571","https://openalex.org/W4226428303","https://openalex.org/W1590308178","https://openalex.org/W2778699561","https://openalex.org/W3015923889","https://openalex.org/W3179294409","https://openalex.org/W159132833","https://openalex.org/W4287102200","https://openalex.org/W4312095954","https://openalex.org/W3160672713"],"abstract_inverted_index":{"Speaker":[0],"embeddings":[1],"achieve":[2],"promising":[3],"results":[4],"on":[5,38,76],"many":[6],"speaker":[7,24,34],"verification":[8],"tasks.Phonetic":[9],"information,":[10],"as":[11],"an":[12],"important":[13],"component":[14],"of":[15,23,83],"speech,":[16],"is":[17],"rarely":[18],"considered":[19],"in":[20,64,70],"the":[21,33,39,51,58,81,84],"extraction":[22,36],"embeddings.In":[25],"this":[26],"paper,":[27],"we":[28],"introduce":[29],"phonetic":[30,44],"information":[31],"to":[32],"embedding":[35],"based":[37],"x-vector":[40,60],"architecture.Two":[41],"methods":[42],"using":[43],"vectors":[45],"and":[46,66,72],"multi-task":[47],"learning":[48],"are":[49],"proposed.On":[50],"Fisher":[52],"dataset,":[53],"our":[54],"best":[55],"system":[56],"outperforms":[57],"original":[59],"approach":[61],"by":[62,67],"20%":[63],"EER,":[65],"15%,":[68],"15%":[69],"minDCF08":[71],"minDCF10,":[73],"respectively.Experiments":[74],"conducted":[75],"NIST":[77],"SRE10":[78],"further":[79],"demonstrate":[80],"effectiveness":[82],"proposed":[85],"methods.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":17}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}