{"id":"https://openalex.org/W2963381607","doi":"https://doi.org/10.21437/interspeech.2017-460","title":"Embedding-Based Speaker Adaptive Training of Deep Neural Networks","display_name":"Embedding-Based Speaker Adaptive Training of Deep Neural Networks","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963381607","doi":"https://doi.org/10.21437/interspeech.2017-460","mag":"2963381607"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5103,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.94399455,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9815999865531921,"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":0.9793000221252441,"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":0.7456207275390625},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.68629390001297},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6808218359947205},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6484478712081909},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5447413325309753},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49618014693260193},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49245747923851013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479423463344574},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45009714365005493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3637263774871826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456207275390625},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.68629390001297},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6808218359947205},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6484478712081909},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5447413325309753},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49618014693260193},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49245747923851013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479423463344574},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45009714365005493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3637263774871826},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1872348600","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2034368206","https://openalex.org/W2048526313","https://openalex.org/W2056738732","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2100969003","https://openalex.org/W2146871184","https://openalex.org/W2150769028","https://openalex.org/W2398054607","https://openalex.org/W2508162385","https://openalex.org/W2963266252","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W1521299571","https://openalex.org/W3096066489","https://openalex.org/W3141593045","https://openalex.org/W1996621592","https://openalex.org/W2134501921","https://openalex.org/W3048257020","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W215245425","https://openalex.org/W4252590334"],"abstract_inverted_index":{"An":[0],"embedding-based":[1],"speaker":[2,22,77],"adaptive":[3,78],"training":[4,103],"(SAT)":[5],"approach":[6],"is":[7,67],"proposed":[8,92],"and":[9],"investigated":[10],"in":[11],"this":[12,20],"paper":[13],"for":[14,62,74],"deep":[15],"neural":[16],"network":[17,38,61,73],"acoustic":[18,79],"modeling.In":[19],"approach,":[21],"embedding":[23],"vectors,":[24],"which":[25],"are":[26,33],"a":[27,30,36,57],"constant":[28],"given":[29],"particular":[31],"speaker,":[32],"mapped":[34],"through":[35],"control":[37,60],"to":[39,44],"layer-dependent":[40],"elementwise":[41],"affine":[42],"transformations":[43],"canonicalize":[45],"the":[46,51,64,71,75,91,100],"internal":[47],"feature":[48],"representations":[49],"at":[50],"output":[52],"of":[53,56],"hidden":[54],"layers":[55],"main":[58,72],"network.The":[59],"generating":[63],"speaker-dependent":[65],"mappings":[66],"jointly":[68],"estimated":[69],"with":[70,106],"overall":[76],"modeling.Experiments":[80],"on":[81],"large":[82],"vocabulary":[83],"continuous":[84],"speech":[85],"recognition":[86],"(LVCSR)":[87],"tasks":[88],"show":[89],"that":[90],"SAT":[93],"scheme":[94],"can":[95],"yield":[96],"superior":[97],"performance":[98],"over":[99],"widely-used":[101],"speaker-aware":[102],"using":[104],"i-vectors":[105],"speaker-adapted":[107],"input":[108],"features.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}