{"id":"https://openalex.org/W2039057510","doi":"https://doi.org/10.1109/icassp.2014.6853887","title":"A novel scheme for speaker recognition using a phonetically-aware deep neural network","display_name":"A novel scheme for speaker recognition using a phonetically-aware deep neural network","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2039057510","doi":"https://doi.org/10.1109/icassp.2014.6853887","mag":"2039057510"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Scheffer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":523,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1695","last_page":"1699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.7989058494567871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878069877624512},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7799387574195862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7701730728149414},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6488227844238281},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6346319913864136},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5761174559593201},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5744991898536682},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5673645734786987},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5267640352249146},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5147114396095276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4769905209541321},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4536423683166504},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4260207414627075},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42148417234420776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30751925706863403}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7989058494567871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878069877624512},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7799387574195862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7701730728149414},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6488227844238281},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6346319913864136},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5761174559593201},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5744991898536682},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5673645734786987},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5267640352249146},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5147114396095276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769905209541321},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4536423683166504},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4260207414627075},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42148417234420776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30751925706863403},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W651157033","https://openalex.org/W1481676178","https://openalex.org/W1521002338","https://openalex.org/W1525353239","https://openalex.org/W2041443702","https://openalex.org/W2041823554","https://openalex.org/W2121812409","https://openalex.org/W2136879537","https://openalex.org/W2142187115","https://openalex.org/W2147147599","https://openalex.org/W2147768505","https://openalex.org/W2150373343","https://openalex.org/W2150769028","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W3145058808","https://openalex.org/W6631422757","https://openalex.org/W6680375658","https://openalex.org/W6681128209","https://openalex.org/W6682034417","https://openalex.org/W6682194325"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1197719229","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,22,86,116,130],"novel":[3],"framework":[4,83,114],"for":[5,14,28,124],"speaker":[6,55,108,125],"recognition":[7,31,56,109],"in":[8,53],"which":[9],"extraction":[10],"of":[11,49,90,133],"sufficient":[12],"statistics":[13],"the":[15,34,37,54,63,70,73,81,94,101,105],"state-of-the-art":[16,87],"i-vector":[17],"model":[18,41],"is":[19,58,115],"driven":[20],"by":[21],"deep":[23],"neural":[24],"network":[25],"(DNN)":[26],"trained":[27],"automatic":[29],"speech":[30,66],"(ASR).":[32],"Specifically,":[33],"DNN":[35],"replaces":[36],"standard":[38,74],"Gaussian":[39],"mixture":[40],"(GMM)":[42],"to":[43,76,85,119],"produce":[44],"frame":[45],"alignments.":[46],"The":[47,112],"use":[48],"an":[50],"ASR-DNN":[51],"system":[52,88],"pipeline":[57],"attractive":[59],"as":[60],"it":[61],"integrates":[62],"information":[64],"from":[65,80,104],"content":[67],"directly":[68],"into":[69],"statistics,":[71],"allowing":[72],"backends":[75],"remain":[77],"unchanged.":[78],"Improvement":[79],"proposed":[82,113],"compared":[84],"are":[89],"30%":[91],"relative":[92],"at":[93],"equal":[95],"error":[96],"rate":[97],"when":[98],"evaluated":[99],"on":[100],"telephone":[102],"conditions":[103],"2012":[106],"NIST":[107],"evaluation":[110],"(SRE).":[111],"successful":[117],"way":[118],"efficiently":[120],"leverage":[121],"transcribed":[122],"data":[123],"recognition,":[126],"thus":[127],"opening":[128],"up":[129],"wide":[131],"spectrum":[132],"research":[134],"directions.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":65},{"year":2019,"cited_by_count":81},{"year":2018,"cited_by_count":93},{"year":2017,"cited_by_count":70},{"year":2016,"cited_by_count":73},{"year":2015,"cited_by_count":40},{"year":2014,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}