{"id":"https://openalex.org/W1909308924","doi":"https://doi.org/10.21437/interspeech.2015-299","title":"A unified deep neural network for speaker and language recognition","display_name":"A unified deep neural network for speaker and language recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1909308924","doi":"https://doi.org/10.21437/interspeech.2015-299","mag":"1909308924"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1504.00923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111923912","display_name":"Fred Richardson","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Richardson","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112042504","display_name":"Douglas A. Reynolds","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas A. Reynolds","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1146","last_page":"1150"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"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":0.993399977684021,"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":0.7707087397575378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7421060800552368},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7410154938697815},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7170147895812988},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6486098170280457},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.552885115146637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5391348600387573},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5305091738700867},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5080735683441162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48990243673324585},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47453606128692627},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4693535268306732},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4608134627342224},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4444595277309418},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40089526772499084},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11377272009849548},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08446785807609558},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06863203644752502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707087397575378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7421060800552368},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7410154938697815},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7170147895812988},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6486098170280457},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.552885115146637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5391348600387573},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5305091738700867},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5080735683441162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48990243673324585},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47453606128692627},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4693535268306732},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4608134627342224},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4444595277309418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40089526772499084},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11377272009849548},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08446785807609558},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06863203644752502},{"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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-299","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1504.00923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.00923","pdf_url":"https://arxiv.org/pdf/1504.00923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:1909308924","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1504.00923.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1504.00923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1504.00923","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1504.00923","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1504.00923","pdf_url":"https://arxiv.org/pdf/1504.00923","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1909308924.pdf","grobid_xml":"https://content.openalex.org/works/W1909308924.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2004497042","https://openalex.org/W2039057510","https://openalex.org/W2072349636","https://openalex.org/W2090958120","https://openalex.org/W2091432990","https://openalex.org/W2148091317","https://openalex.org/W2153181479","https://openalex.org/W2166637769","https://openalex.org/W2181350785","https://openalex.org/W2181594395","https://openalex.org/W2183016404","https://openalex.org/W2184045248","https://openalex.org/W2189248916","https://openalex.org/W2395750323","https://openalex.org/W2402919203"],"related_works":["https://openalex.org/W2150769028","https://openalex.org/W2039057510","https://openalex.org/W2160815625","https://openalex.org/W2183016404","https://openalex.org/W2078169166","https://openalex.org/W2046056978","https://openalex.org/W1524333225","https://openalex.org/W2147768505","https://openalex.org/W2056119007","https://openalex.org/W2041823554","https://openalex.org/W2408021097","https://openalex.org/W2121812409","https://openalex.org/W2406312423","https://openalex.org/W2395750323","https://openalex.org/W2290689761","https://openalex.org/W2185814970","https://openalex.org/W2136879537","https://openalex.org/W1528954144","https://openalex.org/W2995240650","https://openalex.org/W2962832278"],"abstract_inverted_index":{"Learned":[0],"feature":[1],"representations":[2],"and":[3,22,43,75],"sub-phoneme":[4],"posteriors":[5],"from":[6],"Deep":[7],"Neural":[8],"Networks":[9],"(DNNs)":[10],"have":[11],"been":[12],"used":[13],"separately":[14],"to":[15,52],"produce":[16],"significant":[17],"performance":[18,55],"gains":[19,33],"for":[20,40,71,87],"speaker":[21,42,64],"language":[23,44],"recognition":[24,65],"tasks.":[25],"In":[26],"this":[27],"work":[28],"we":[29],"show":[30],"how":[31],"these":[32],"are":[34],"possible":[35],"using":[36],"a":[37],"single":[38],"DNN":[39,48],"both":[41],"recognition.":[45],"The":[46],"unified":[47],"approach":[49],"is":[50],"shown":[51],"yield":[53],"substantial":[54],"improvements":[56],"on":[57,76],"the":[58,59,72,77,88],"2013":[60],"Domain":[61],"Adaptation":[62],"Challenge":[63],"task":[66],"(55%":[67],"reduction":[68,84],"in":[69,85],"EER":[70,86],"out-of-domain":[73],"condition)":[74],"NIST":[78],"2011":[79],"Language":[80],"Recognition":[81],"Evaluation":[82],"(48%":[83],"30s":[89],"test":[90],"condition).":[91]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}