{"id":"https://openalex.org/W2183016404","doi":"https://doi.org/10.21437/odyssey.2014-44","title":"Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition","display_name":"Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition","publication_year":2014,"publication_date":"2014-06-16","ids":{"openalex":"https://openalex.org/W2183016404","doi":"https://doi.org/10.21437/odyssey.2014-44","mag":"2183016404"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2014-44","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-44","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","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/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061517549","display_name":"Pierre Ouellet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Ouellet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114009216","display_name":"Vishwa Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishwa Gupta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088749621","display_name":"Jahangir Alam","orcid":"https://orcid.org/0000-0003-4174-9862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jahangir Alam","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036466893"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":39.3253,"has_fulltext":false,"cited_by_count":215,"citation_normalized_percentile":{"value":0.99816068,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"298"},"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":0.9976999759674072,"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":0.9962999820709229,"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":0.7151569128036499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6307368874549866},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5994113683700562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.564184308052063},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4476560056209564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41917839646339417},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4187338352203369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151569128036499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6307368874549866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5994113683700562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564184308052063},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4476560056209564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41917839646339417},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4187338352203369}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2014-44","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2014-44","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2014)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.1244","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.1244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.uef.fi/odyssey2014/program/pdfs/28.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W49975404","https://openalex.org/W176831429","https://openalex.org/W1802356529","https://openalex.org/W2015633636","https://openalex.org/W2091432990","https://openalex.org/W2106554350","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2131342762","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2184045248","https://openalex.org/W2395750323","https://openalex.org/W2399828378"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2499802997","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"We":[0],"examine":[1],"the":[2,21,26,30,37,42,59,74,84,88,103,109,127,135,159,174],"use":[3],"of":[4,19,39,46,108,141],"Deep":[5],"Neural":[6],"Networks":[7],"(DNN)":[8],"in":[9,70,91],"extracting":[10],"Baum-Welch":[11,68],"statistics":[12,69],"for":[13],"i-vector-based":[14],"text-independent":[15],"speaker":[16,94],"recognition.":[17],"Instead":[18],"training":[20],"uni-versal":[22],"background":[23],"model":[24],"using":[25],"standard":[27,60,104,110,136],"EM":[28],"algorithm,":[29],"components":[31],"are":[32,48,55,139],"predefined":[33],"and":[34,77,117],"correspond":[35],"to":[36,64,72,86,134],"set":[38],"triphone":[40,98],"states,":[41],"posterior":[43],"occupancy":[44],"probabilities":[45],"which":[47,92,100],"mod-eled":[49],"by":[50],"a":[51,118,166],"DNN.":[52],"Those":[53],"assignments":[54],"then":[56],"combined":[57],"with":[58,114,149,165,173],"60-dim":[61],"MFCC":[62],"features":[63],"calculate":[65],"first":[66],"order":[67,71],"train":[73],"i-vector":[75],"extractor":[76],"ex-tract":[78],"i-vectors.":[79,111],"The":[80],"DNN-based":[81],"assignment":[82],"force":[83],"i-vectors":[85,129,176],"capture":[87],"idiosyncratic":[89],"way":[90],"each":[93,96],"pro-nounces":[95],"particular":[97],"state,":[99],"can":[101],"enrich":[102],"short-term":[105],"spectral":[106],"representation":[107],"After":[112],"experimenting":[113],"Switchboard":[115],"data":[116],"baseline":[119,175],"PLDA":[120],"classifier,":[121],"our":[122],"results":[123],"showed":[124],"that":[125,152],"although":[126],"proposed":[128],"yield":[130],"inferior":[131],"performance":[132,172],"compared":[133],"ones,":[137],"they":[138,153],"capable":[140],"attaining":[142],"16":[143],"%":[144],"relative":[145],"improvement":[146],"when":[147],"fused":[148],"them,":[150],"meaning":[151],"carry":[154],"useful":[155],"com-plementary":[156],"information":[157],"about":[158],"speaker\u2019s":[160],"identity.":[161],"A":[162],"further":[163],"experiment":[164],"different":[167],"DNN":[168],"configuration":[169],"attained":[170],"com-parable":[171],"on":[177],"NIST":[178],"2012":[179],"(condition":[180],"C2,":[181],"female).":[182],"1.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}