{"id":"https://openalex.org/W2005054044","doi":"https://doi.org/10.1109/icassp.2002.5743953","title":"A mixture linear model with target-directed dynamics for spontaneous speech recognition","display_name":"A mixture linear model with target-directed dynamics for spontaneous speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2005054044","doi":"https://doi.org/10.1109/icassp.2002.5743953","mag":"2005054044"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743953","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5018625471","display_name":"Zaremba Jeff","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeff Z. Ma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Cambridge, MA, USA","BBN Technologies , Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technologies , Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Microsoft Research, University of Waterloo, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Microsoft Research, University of Waterloo, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018625471"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6483,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59049208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9889000058174133,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6909135580062866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5779094696044922},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5261282920837402},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5135179162025452},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4944760799407959},{"id":"https://openalex.org/keywords/piecewise-linear-function","display_name":"Piecewise linear function","score":0.4911331832408905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4672626852989197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45924806594848633},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.4317765235900879},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.43083545565605164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3633562922477722},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36325550079345703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23523399233818054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6909135580062866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5779094696044922},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5261282920837402},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5135179162025452},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4944760799407959},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.4911331832408905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4672626852989197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45924806594848633},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.4317765235900879},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.43083545565605164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3633562922477722},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36325550079345703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23523399233818054},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"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/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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743953","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W42107399","https://openalex.org/W230535489","https://openalex.org/W1507322379","https://openalex.org/W1963718895","https://openalex.org/W2083393647","https://openalex.org/W2092684968","https://openalex.org/W2167465665","https://openalex.org/W2465919943","https://openalex.org/W4247537702","https://openalex.org/W4285719527","https://openalex.org/W6609063550","https://openalex.org/W6719392674"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2133947431","https://openalex.org/W2490196280","https://openalex.org/W3182827720","https://openalex.org/W1596838019","https://openalex.org/W3208509670","https://openalex.org/W2109304297","https://openalex.org/W2100864966","https://openalex.org/W2083709218","https://openalex.org/W4323366562"],"abstract_inverted_index":{"In":[0],"this":[1,132],"paper,":[2],"a":[3,49,65,141,146,162],"mixture":[4],"linear":[5,18,43,66],"dynamic":[6,19,29,44,56],"model":[7,45,95,121,134],"(MLDM)":[8],"for":[9,71,92],"speech":[10],"recognition":[11,125],"is":[12,46,58,69,90],"developed":[13,91],"and":[14,31,38,64,120],"evaluated,":[15],"where":[16,52,97],"several":[17],"systems":[20],"are":[21,101,127],"combined":[22],"(mixed)":[23],"to":[24,75,103,130],"represent":[25],"different":[26],"vocaltract-resonance":[27],"(VTR)":[28],"behavior":[30],"the":[32,36,39,53,61,72,79,86,94,98,107,113,117,136,150,155],"mapping":[33,81],"relationships":[34],"between":[35],"VTRs":[37],"acoustic":[40,153],"observation.":[41],"Each":[42],"formulated":[47],"as":[48],"stale-space":[50],"system,":[51],"VTR's":[54],"target-directed":[55],"property":[57],"incorporated":[59],"in":[60,116,140],"state":[62],"equation":[63,74],"regression":[67],"function":[68],"used":[70],"observation":[73],"piecewise":[76],"linearly":[77],"approximate":[78],"nonlinear":[80],"relationship.":[82],"A":[83],"version":[84],"of":[85,164],"generalized":[87],"EM":[88],"algorithm":[89],"learning":[93,119],"parameters,":[96],"VTR":[99],"targets":[100],"constrained":[102],"change":[104],"only":[105],"at":[106,112],"segmental":[108],"level":[109],"(rather":[110],"than":[111],"frame":[114],"level)":[115],"parameter":[118],"scoring":[122],"algorithms.":[123],"Speech":[124],"experiments":[126],"carried":[128],"out":[129],"evaluate":[131],"new":[133,156],"using":[135,149],"N-best":[137],"re-scoring":[138],"paradigm":[139],"Switchboard":[142],"task.":[143],"Compared":[144],"with":[145],"baseline":[147],"recognizer":[148,157],"triphone":[151],"HMM":[152],"model,":[154],"demonstrates":[158],"superior":[159],"performance":[160],"under":[161],"number":[163],"experimental":[165],"conditions.":[166]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}