{"id":"https://openalex.org/W2079623482","doi":"https://doi.org/10.1109/asru.2013.6707705","title":"Speaker adaptation of neural network acoustic models using i-vectors","display_name":"Speaker adaptation of neural network acoustic models using i-vectors","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2079623482","doi":"https://doi.org/10.1109/asru.2013.6707705","mag":"2079623482"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Nahamoo","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM T. J. Watson Research Center, NY","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079994647"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":95.911,"has_fulltext":false,"cited_by_count":606,"citation_normalized_percentile":{"value":0.99966882,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"59"},"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":0.998199999332428,"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":0.9979000091552734,"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":0.7813991904258728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7554023265838623},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6148378849029541},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.614726722240448},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5828356742858887},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.564978837966919},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5408125519752502},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4917741119861603},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44372329115867615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4135705828666687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34832122921943665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09625473618507385},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06742435693740845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813991904258728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7554023265838623},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6148378849029541},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.614726722240448},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5828356742858887},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.564978837966919},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5408125519752502},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4917741119861603},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44372329115867615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4135705828666687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34832122921943665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09625473618507385},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06742435693740845},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322748","display_name":"Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Brn\u011b","ror":"https://ror.org/03613d656"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1482750548","https://openalex.org/W1523142923","https://openalex.org/W1979058968","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2022608894","https://openalex.org/W2024919734","https://openalex.org/W2058641082","https://openalex.org/W2062164080","https://openalex.org/W2087006792","https://openalex.org/W2146635662","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2189248916","https://openalex.org/W2196568223","https://openalex.org/W2265396709","https://openalex.org/W2270033225","https://openalex.org/W2289089770","https://openalex.org/W2403195671","https://openalex.org/W4230607426","https://openalex.org/W6608353291"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"We":[0],"propose":[1],"to":[2,10,23,48,52,102],"adapt":[3],"deep":[4],"neural":[5],"network":[6,25],"(DNN)":[7],"acoustic":[8,31],"models":[9],"a":[11,43,63,79,131],"target":[12],"speaker":[13,16,45,54,73,92],"by":[14],"supplying":[15],"identity":[17],"vectors":[18],"(i-vectors)":[19],"as":[20],"input":[21],"features":[22,32,75,94,107,127,146],"the":[24,29,40,113],"in":[26,83,100,135],"parallel":[27],"with":[28,112],"regular":[30],"for":[33,42],"ASR.":[34],"For":[35],"both":[36],"training":[37,140],"and":[38,55,76,110,128],"test,":[39],"i-vector":[41],"given":[44],"is":[46,120],"concatenated":[47],"every":[49],"frame":[50],"belonging":[51],"that":[53,69,115],"changes":[56],"across":[57],"different":[58],"speakers.":[59],"Experimental":[60],"results":[61],"on":[62,72,91,105,125,144],"Switchboard":[64],"300":[65],"hours":[66],"corpus":[67],"show":[68],"DNNs":[70,103],"trained":[71,90,104,124,143],"independent":[74,93],"i-vectors":[77,129],"achieve":[78,130],"10%":[80],"relative":[81,133],"improvement":[82,134],"word":[84],"error":[85],"rate":[86],"(WER)":[87],"over":[88,141],"networks":[89,97,123,142],"only.":[95,147],"These":[96],"are":[98],"comparable":[99],"performance":[101],"speaker-adapted":[106,126,145],"(with":[108],"VTLN":[109],"FMLLR)":[111],"advantage":[114],"only":[116],"one":[117],"decoding":[118],"pass":[119],"needed.":[121],"Furthermore,":[122],"5-6%":[132],"WER":[136],"after":[137],"hessian-free":[138],"sequence":[139]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":59},{"year":2019,"cited_by_count":88},{"year":2018,"cited_by_count":78},{"year":2017,"cited_by_count":71},{"year":2016,"cited_by_count":92},{"year":2015,"cited_by_count":66},{"year":2014,"cited_by_count":35}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}