{"id":"https://openalex.org/W2885329609","doi":"https://doi.org/10.21437/interspeech.2018-1696","title":"On Learning Vocal Tract System Related Speaker Discriminative Information from Raw Signal Using CNNs","display_name":"On Learning Vocal Tract System Related Speaker Discriminative Information from Raw Signal Using CNNs","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2885329609","doi":"https://doi.org/10.21437/interspeech.2018-1696","mag":"2885329609"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1696","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1696","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/256307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047091215","display_name":"Hannah Muckenhirn","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Hannah Muckenhirn","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016330764","display_name":"S\u00e9bastien Marcel","orcid":"https://orcid.org/0000-0002-2497-9140"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sebastien Marcel","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047091215"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.466,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86563805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1116","last_page":"1120"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.9984999895095825,"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/vocal-tract","display_name":"Vocal tract","score":0.8247215747833252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8087927103042603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7556737661361694},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7230429649353027},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.604403018951416},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6004361510276794},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5954357981681824},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5757920742034912},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5245625972747803},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49390560388565063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49327749013900757},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4910774230957031},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.42070698738098145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3500329256057739},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3075367212295532}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8247215747833252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087927103042603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7556737661361694},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7230429649353027},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.604403018951416},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6004361510276794},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5954357981681824},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5757920742034912},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5245625972747803},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49390560388565063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49327749013900757},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4910774230957031},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.42070698738098145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3500329256057739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3075367212295532},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1696","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1696","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"},{"id":"pmh:oai:infoscience.epfl.ch:256307","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256307","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:256307","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256307","raw_type":"Text"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1666984270","https://openalex.org/W1999405202","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2070696251","https://openalex.org/W2107638917","https://openalex.org/W2117130368","https://openalex.org/W2121812409","https://openalex.org/W2134689131","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2172179449","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2408093180","https://openalex.org/W2513345070","https://openalex.org/W2566781703","https://openalex.org/W2592641653","https://openalex.org/W2726515241","https://openalex.org/W2738359832","https://openalex.org/W2747238065","https://openalex.org/W2770454110","https://openalex.org/W2963175699","https://openalex.org/W4233131682"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2131046383","https://openalex.org/W2021612972"],"abstract_inverted_index":{"In":[0,32,66],"a":[1,83,103],"recent":[2],"work,":[3],"we":[4,75,126],"have":[5],"shown":[6],"that":[7,49,79,101,128,152],"speaker":[8,111,141],"verification":[9,142],"systems":[10],"can":[11],"be":[12],"built":[13],"where":[14],"both":[15],"features":[16],"and":[17,120,144],"classifiers":[18],"are":[19],"directly":[20],"learned":[21],"from":[22,71],"the":[23,35,40,50,67,94,129,149],"raw":[24],"speech":[25,72,89],"signal":[26],"with":[27,98],"convolutional":[28],"neural":[29],"networks":[30],"(CNNs).":[31],"this":[33],"framework,":[34],"training":[36],"phase":[37],"also":[38],"decides":[39],"block":[41],"processing":[42],"through":[43],"cross":[44],"validation.":[45],"It":[46],"was":[47],"found":[48],"first":[51,95],"convolution":[52,96],"layer,":[53,97],"which":[54,86],"processes":[55],"about":[56],"20":[57],"ms":[58],"speech,":[59],"learns":[60],"to":[61,81,148],"model":[62],"fundamental":[63,154],"frequency":[64,155],"information.":[65,113,156],"present":[68],"paper,":[69],"inspired":[70],"recognition":[73],"studies,":[74],"build":[76],"further":[77],"on":[78,117,122,135],"framework":[80],"design":[82],"CNN-based":[84,150],"system,":[85],"models":[87,153],"sub-segmental":[88],"(about":[90],"2ms":[91],"speech)":[92],"in":[93],"an":[99],"hypothesis":[100],"such":[102],"system":[104,109,131,143,151],"should":[105],"learn":[106],"vocal":[107],"tract":[108],"related":[110],"discriminative":[112],"Through":[114],"experimental":[115],"studies":[116],"Voxforge":[118],"corpus":[119],"analysis":[121],"American":[123],"vowel":[124],"dataset,":[125],"show":[127],"proposed":[130],"(a)":[132],"indeed":[133],"focuses":[134],"formant":[136],"regions,":[137],"(b)":[138],"yields":[139],"competitive":[140],"(c)":[145],"is":[146],"complementary":[147]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}