{"id":"https://openalex.org/W2640876020","doi":"https://doi.org/10.1109/icassp.2017.7953196","title":"Deep neural networks based speaker modeling at different levels of phonetic granularity","display_name":"Deep neural networks based speaker modeling at different levels of phonetic granularity","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2640876020","doi":"https://doi.org/10.1109/icassp.2017.7953196","mag":"2640876020"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100571324","display_name":"Yao Tian","orcid":null},"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":"Yao Tian","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052057753","display_name":"Meng Cai","orcid":"https://orcid.org/0000-0002-0711-5949"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Cai","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"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":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"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":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.969,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80252232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5440","last_page":"5444"},"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":0.9969000220298767,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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":0.7947142124176025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7198248505592346},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7034784555435181},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6073657274246216},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5975374579429626},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5605752468109131},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.526150643825531},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4935542345046997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49122732877731323},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4794448912143707},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.457744300365448},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4565557539463043},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42947307229042053},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42864349484443665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947142124176025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7198248505592346},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7034784555435181},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6073657274246216},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5975374579429626},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5605752468109131},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.526150643825531},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4935542345046997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49122732877731323},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4794448912143707},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.457744300365448},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4565557539463043},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42947307229042053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42864349484443665},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1521002338","https://openalex.org/W1525353239","https://openalex.org/W1993882792","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2107638917","https://openalex.org/W2121812409","https://openalex.org/W2130633305","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2173092938","https://openalex.org/W2183016404","https://openalex.org/W2187089797","https://openalex.org/W2187387698","https://openalex.org/W2395750323","https://openalex.org/W2397346386","https://openalex.org/W2406312423","https://openalex.org/W2407857848","https://openalex.org/W2515626571","https://openalex.org/W6603616073","https://openalex.org/W6631422757","https://openalex.org/W6685376867","https://openalex.org/W6686491854","https://openalex.org/W6712282327","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2018623685","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W1521299571","https://openalex.org/W1197719229","https://openalex.org/W468945283","https://openalex.org/W2381158726","https://openalex.org/W2316548414","https://openalex.org/W1992796048","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Recently,":[0],"a":[1,78,90,96],"hybrid":[2],"deep":[3],"neural":[4],"network/i-vector":[5],"framework":[6],"has":[7],"been":[8],"proved":[9],"effective":[10],"for":[11,29,150],"speaker":[12,48,151,157],"verification,":[13],"where":[14],"the":[15,41,71,74,114,128],"DNN":[16,119],"trained":[17],"to":[18,25,38,47,77,101,113,155],"predict":[19],"tied-triphone":[20,64],"states":[21],"(senones)":[22],"is":[23,82],"used":[24],"produce":[26],"frame":[27,60],"alignments":[28],"sufficient":[30],"statistics":[31],"extraction.":[32],"In":[33],"this":[34],"work,":[35],"in":[36],"order":[37],"better":[39,154],"understand":[40],"impact":[42],"of":[43,53,73,105],"different":[44,106,156],"phonetic":[45,54,80,103,142,148],"precision":[46],"verification":[49,158],"tasks,":[50],"three":[51],"levels":[52],"granularity":[55,107],"are":[56,63,124],"evaluated":[57],"when":[58],"doing":[59],"alignments,":[61],"which":[62],"state,":[65],"monophone":[66],"state":[67],"and":[68,98,144],"monophone.":[69],"And":[70],"distribution":[72],"features":[75],"associated":[76],"given":[79],"unit":[81,149],"further":[83],"modeled":[84],"with":[85,139],"multiple":[86],"Gaussians":[87,146],"rather":[88],"than":[89],"single":[91],"Gaussian.":[92],"We":[93],"also":[94],"propose":[95],"fast":[97],"efficient":[99],"way":[100],"generate":[102],"units":[104,143],"by":[108],"tying":[109],"DNN's":[110],"outputs":[111],"according":[112],"clustering":[115],"results":[116],"based":[117],"on":[118,127],"derived":[120],"senone":[121],"embeddings.":[122],"Experiments":[123],"carried":[125],"out":[126],"NIST":[129],"SRE":[130],"2008":[131],"female":[132],"tasks.":[133,159],"Results":[134],"show":[135],"that":[136],"using":[137],"DNNs":[138],"less":[140],"precise":[141],"more":[145],"per":[147],"modeling":[152],"generalize":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}