{"id":"https://openalex.org/W2486340537","doi":"https://doi.org/10.1109/taslp.2016.2594255","title":"Maximum Likelihood Nonlinear Transformations Based on Deep Neural Networks","display_name":"Maximum Likelihood Nonlinear Transformations Based on Deep Neural Networks","publication_year":2016,"publication_date":"2016-07-27","ids":{"openalex":"https://openalex.org/W2486340537","doi":"https://doi.org/10.1109/taslp.2016.2594255","mag":"2486340537"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2594255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2594255","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83821032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":"11","first_page":"2023","last_page":"2031"},"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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7279899716377258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5959429740905762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.561848521232605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5237619280815125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5025207996368408},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4995408058166504},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47809407114982605},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4724448323249817},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.465087354183197},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4488353133201599},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4458007216453552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33023595809936523}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7279899716377258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5959429740905762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.561848521232605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5237619280815125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5025207996368408},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4995408058166504},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47809407114982605},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4724448323249817},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.465087354183197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4488353133201599},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4458007216453552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33023595809936523},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2594255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2594255","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W182014611","https://openalex.org/W1506806321","https://openalex.org/W1509793305","https://openalex.org/W1529602138","https://openalex.org/W1537275613","https://openalex.org/W1599512239","https://openalex.org/W1663973292","https://openalex.org/W1979651826","https://openalex.org/W1988115241","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2006722592","https://openalex.org/W2014208555","https://openalex.org/W2034368206","https://openalex.org/W2038507080","https://openalex.org/W2039285212","https://openalex.org/W2049633694","https://openalex.org/W2062164080","https://openalex.org/W2078528584","https://openalex.org/W2082474452","https://openalex.org/W2086796102","https://openalex.org/W2100969003","https://openalex.org/W2103496339","https://openalex.org/W2106554350","https://openalex.org/W2113249522","https://openalex.org/W2122272452","https://openalex.org/W2125234026","https://openalex.org/W2125378570","https://openalex.org/W2136439176","https://openalex.org/W2137983211","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150907703","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2164931619","https://openalex.org/W2184045248","https://openalex.org/W2294059674","https://openalex.org/W2308181013","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2404166326","https://openalex.org/W3020882730","https://openalex.org/W3146803896","https://openalex.org/W4205634987","https://openalex.org/W6696761078","https://openalex.org/W6711962127","https://openalex.org/W6713280142","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2995886640","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1578916557"],"abstract_inverted_index":{"Feature":[0],"transformations":[1,30,46,161],"are":[2,31,110],"commonly":[3],"used":[4],"in":[5,67,162,168],"speech":[6,62,172],"recognition":[7,173],"to":[8,21,60,83,97,130],"account":[9],"for":[10],"distribution":[11],"mismatches":[12],"between":[13],"the":[14,49,55,92,98,100,103,113,158,180],"source":[15],"and":[16,65,102,165],"target":[17],"domains":[18],"(also":[19],"referred":[20],"as":[22,135],"covariate":[23],"shift).":[24],"Linear":[25],"(affine)":[26],"or":[27],"piecewise":[28],"linear":[29,85,185],"typically":[32],"considered.":[33],"In":[34,122],"this":[35],"paper,":[36],"we":[37],"present":[38],"deep":[39,125],"neural":[40],"network":[41,79],"(DNN)":[42],"based":[43,118],"nonlinear":[44,144,160],"feature":[45,63],"estimated":[47],"under":[48],"maximum":[50,183],"likelihood":[51,184],"criterion.":[52],"We":[53],"use":[54],"hidden":[56],"Markov":[57],"model":[58,61,75],"(HMM)":[59],"sequences":[64],"features":[66],"each":[68,141],"HMM":[69],"state":[70,108],"assume":[71],"a":[72,84,89,124,133,136,143,152],"Gaussian":[73],"mixture":[74],"(GMM)":[76],"distribution.":[77],"The":[78],"is":[80,128],"pre-trained":[81],"close":[82],"transformation":[86,145],"followed":[87],"by":[88],"fine-tuning":[90],"using":[91,112,151],"gradient":[93],"descent":[94],"algorithm.":[95],"Due":[96],"nonlinearity,":[99],"gradients":[101],"partition":[104],"functions":[105],"of":[106,138,157],"GMM-HMM":[107],"distributions":[109],"evaluated":[111],"Monte":[114],"Carlo":[115],"(MC)":[116],"method":[117],"on":[119],"importance":[120],"sampling.":[121],"addition,":[123],"stacked":[126],"architecture":[127],"proposed":[129,159],"hierarchically":[131],"build":[132],"DNN":[134],"series":[137],"sub-networks":[139],"with":[140],"representing":[142],"itself,":[146],"which":[147],"can":[148],"be":[149],"learned":[150],"block-wise":[153],"learning":[154],"strategy.":[155],"Applications":[156],"speaker/environment":[163],"adaptation":[164],"acoustic":[166],"modeling":[167],"large":[169],"vocabulary":[170],"continuous":[171],"tasks":[174],"show":[175],"its":[176],"superior":[177],"performance":[178],"over":[179],"widely-used":[181],"constrained":[182],"regression":[186],"(CMLLR).":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}