{"id":"https://openalex.org/W3015596621","doi":"https://doi.org/10.1109/icassp40776.2020.9052957","title":"TDMF: Task-Driven Multilevel Framework for End-to-End Speaker Verification","display_name":"TDMF: Task-Driven Multilevel Framework for End-to-End Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015596621","doi":"https://doi.org/10.1109/icassp40776.2020.9052957","mag":"3015596621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Chen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100418547"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51655464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","issue":null,"first_page":"6809","last_page":"6813"},"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":0.9943000078201294,"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":0.9868999719619751,"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/speaker-verification","display_name":"Speaker verification","score":0.8374737501144409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806833028793335},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6028486490249634},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5919020175933838},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5703675746917725},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5092936754226685},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49115630984306335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46928274631500244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668503403663635},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4563291072845459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45222973823547363},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4375010132789612},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.42727023363113403},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4229945242404938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4148532450199127},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3931959271430969}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8374737501144409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806833028793335},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6028486490249634},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5919020175933838},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5703675746917725},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5092936754226685},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49115630984306335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46928274631500244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668503403663635},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4563291072845459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45222973823547363},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4375010132789612},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.42727023363113403},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4229945242404938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4148532450199127},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3931959271430969},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/10","score":0.6600000262260437,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2069900289","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2125027820","https://openalex.org/W2137658434","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2397133385","https://openalex.org/W2401194241","https://openalex.org/W2584329820","https://openalex.org/W2726515241","https://openalex.org/W2746692108","https://openalex.org/W2748488820","https://openalex.org/W2883426725","https://openalex.org/W2890964092","https://openalex.org/W2897430947","https://openalex.org/W2962767738","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2963173190","https://openalex.org/W2963382494","https://openalex.org/W6648737282","https://openalex.org/W6713135114","https://openalex.org/W6740167877","https://openalex.org/W6742911084","https://openalex.org/W6753583402","https://openalex.org/W6809554498"],"related_works":["https://openalex.org/W2018623685","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2316548414","https://openalex.org/W4235705411","https://openalex.org/W1992796048","https://openalex.org/W2972909277","https://openalex.org/W1516392727"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"task-driven":[4],"multilevel":[5],"framework":[6,130],"(TDMF)":[7],"is":[8],"proposed":[9,59],"for":[10],"end-to-end":[11,82],"speaker":[12,26],"verification.":[13],"The":[14,113],"TDMF":[15,60,104,119],"has":[16,22],"four":[17],"layers,":[18],"and":[19,47,90,131],"each":[20,67],"layer":[21],"different":[23,79],"effects":[24],"on":[25],"models":[27],"or":[28],"representations":[29],"to":[30],"implement":[31],"the":[32,54,58,63,71,75,94,100,103,110,118,127],"functions":[33],"of":[34,66,126],"universal":[35],"background":[36],"model":[37,41,45],"(UBM),":[38],"Gaussian":[39],"mixture":[40],"(GMM),":[42],"total":[43],"variability":[44],"(TVM)":[46],"probabilistic":[48],"linear":[49],"discriminant":[50],"analysis":[51],"(PLDA).":[52],"Unlike":[53],"typical":[55,128],"i-vector":[56,129],"method,":[57],"can":[61,105,120],"supervise":[62],"optimal":[64],"solution":[65],"phase":[68],"(layer)":[69],"towards":[70],"direction":[72],"required":[73],"by":[74],"PLDA":[76],"classifier.":[77],"Moreover,":[78],"from":[80],"most":[81],"neural":[83,134],"network":[84],"approaches,":[85],"which":[86],"extract":[87],"embeddings":[88,98],"first":[89],"then":[91],"additionally":[92],"calculate":[93],"distance":[95],"between":[96],"two":[97],"as":[99],"verification":[101],"score,":[102],"directly":[106],"provide":[107],"scores":[108],"via":[109],"fourth-layer":[111],"PLDA.":[112],"experimental":[114],"results":[115],"show":[116],"that":[117,125],"achieve":[121],"better":[122],"performance":[123],"than":[124],"VGG-M":[132],"convolutional":[133],"networks":[135],"(CNN)":[136],"framework.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}