{"id":"https://openalex.org/W2056445351","doi":"https://doi.org/10.1109/slt.2014.7078566","title":"Speaker adaptation of deep neural networks using a hierarchy of output layers","display_name":"Speaker adaptation of deep neural networks using a hierarchy of output layers","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2056445351","doi":"https://doi.org/10.1109/slt.2014.7078566","mag":"2056445351"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5028120017","display_name":"Ryan Price","orcid":"https://orcid.org/0000-0003-0624-6629"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryan Price","raw_affiliation_strings":["Tokvo Institute of Technology, Japan","Tokyo institute of Technology (Japan)"],"affiliations":[{"raw_affiliation_string":"Tokvo Institute of Technology, Japan","institution_ids":[]},{"raw_affiliation_string":"Tokyo institute of Technology (Japan)","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109220146","display_name":"Ken-ichi Iso","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ken-ichi Iso","raw_affiliation_strings":["Yahoo Japan Corporation, Japan","Yahoo Japan Corp., Japan"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Japan","institution_ids":[]},{"raw_affiliation_string":"Yahoo Japan Corp., Japan","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Tokvo Institute of Technology, Japan","Tokyo institute of Technology (Japan)"],"affiliations":[{"raw_affiliation_string":"Tokvo Institute of Technology, Japan","institution_ids":[]},{"raw_affiliation_string":"Tokyo institute of Technology (Japan)","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028120017"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":5.9082,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96169225,"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":"153","last_page":"158"},"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":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/adaptation","display_name":"Adaptation (eye)","score":0.7304350137710571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130539417266846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6799864768981934},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6367923617362976},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.622567355632782},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6103935837745667},{"id":"https://openalex.org/keywords/neural-adaptation","display_name":"Neural adaptation","score":0.5821556448936462},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5793685913085938},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5728305578231812},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5161288976669312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5037545561790466},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5021452903747559},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4808821976184845},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4591905176639557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4501769244670868},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4410630464553833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13505861163139343}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7304350137710571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130539417266846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6799864768981934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6367923617362976},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.622567355632782},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6103935837745667},{"id":"https://openalex.org/C2780112520","wikidata":"https://www.wikidata.org/wiki/Q5353379","display_name":"Neural adaptation","level":3,"score":0.5821556448936462},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5793685913085938},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5728305578231812},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5161288976669312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037545561790466},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5021452903747559},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4808821976184845},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4591905176639557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4501769244670868},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4410630464553833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13505861163139343},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"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:10.1109/slt.2014.7078566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004082020","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100677924","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. Spoken Language Technology (SLT) Workshop","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1513862252","https://openalex.org/W1537275613","https://openalex.org/W1599512239","https://openalex.org/W1722135069","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2015633636","https://openalex.org/W2056825827","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2122677231","https://openalex.org/W2126002878","https://openalex.org/W2146871184","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2162042984","https://openalex.org/W2401524124","https://openalex.org/W6654250109","https://openalex.org/W6684010798"],"related_works":["https://openalex.org/W4239286941","https://openalex.org/W2053269318","https://openalex.org/W2088845016","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1480162782"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"used":[4],"for":[5,33],"acoustic":[6],"modeling":[7],"in":[8,123,187],"speech":[9],"recognition":[10,142],"often":[11,37],"have":[12],"a":[13,40,108,177],"very":[14],"large":[15,41],"number":[16],"of":[17,30,43,59,103,111,120,131,151,160,171,195],"output":[18,96,105,136],"units":[19],"corresponding":[20],"to":[21,75,83,107],"context":[22],"dependent":[23],"(CD)":[24],"triphone":[25],"HMM":[26],"states.":[27],"The":[28],"amount":[29],"data":[31],"available":[32],"speaker":[34,70,85],"adaptation":[35,71,125,196],"is":[36,139],"limited":[38],"so":[39],"majority":[42],"these":[44,77],"CD":[45,61,152,172],"states":[46,62,78,122,153,173],"may":[47],"not":[48],"be":[49,80],"observed":[50],"during":[51,68],"adaptation.":[52],"In":[53],"this":[54,90,161],"case,":[55],"the":[56,73,84,100,118,124,134,148,158,165,168],"posterior":[57,145],"probabilities":[58,146],"unseen":[60,121],"are":[63,154],"only":[64],"pushed":[65],"towards":[66],"zero":[67],"DNN":[69,104],"and":[72,182],"ability":[74],"predict":[76],"can":[79],"degraded":[81],"relative":[82,185],"independent":[86],"network.":[87],"We":[88,156],"address":[89],"problem":[91],"by":[92,129],"appending":[93],"an":[94],"additional":[95],"layer":[97],"which":[98,138],"maps":[99],"original":[101,149,169],"set":[102,110,150,170],"classes":[106,113],"smaller":[109],"phonetic":[112],"(e.g.":[114],"monophones)":[115],"thereby":[116],"reducing":[117],"occurrences":[119],"data.":[126,197],"Adaptation":[127],"proceeds":[128],"backpropagation":[130],"errors":[132],"from":[133],"new":[135],"layer,":[137],"disregarded":[140],"at":[141],"time":[143],"when":[144],"over":[147,163],"used.":[155],"demonstrate":[157],"benefits":[159],"approach":[162],"adapting":[164],"network":[166],"with":[167,191],"using":[174],"experiments":[175],"on":[176],"Japanese":[178],"voice":[179],"search":[180],"task":[181],"obtain":[183],"5.03%":[184],"reduction":[186],"character":[188],"error":[189],"rate":[190],"approximately":[192],"60":[193],"seconds":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}