{"id":"https://openalex.org/W2148622792","doi":"https://doi.org/10.1109/icassp.2005.1415119","title":"A Hidden Trajectory Model with Bi-directional Target-Filtering: Cascaded vs. Integrated Implementation for Phonetic Recognition","display_name":"A Hidden Trajectory Model with Bi-directional Target-Filtering: Cascaded vs. Integrated Implementation for Phonetic Recognition","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2148622792","doi":"https://doi.org/10.1109/icassp.2005.1415119","mag":"2148622792"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/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":true,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682962","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-9164-5802"},"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":"Xiang Li","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"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":"A. Acero","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100671324"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":2.5794,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89732761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"337","last_page":"340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9969000220298767,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251995801925659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6928424835205078},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6898826956748962},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5825228095054626},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5273949503898621},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5150875449180603},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5134761929512024},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4705524742603302},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4603971838951111},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4305742681026459},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41615211963653564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41396594047546387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4127761125564575},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4105774164199829},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26869964599609375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251995801925659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6928424835205078},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6898826956748962},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5825228095054626},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5273949503898621},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5150875449180603},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5134761929512024},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4705524742603302},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4603971838951111},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4305742681026459},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41615211963653564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41396594047546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4127761125564575},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4105774164199829},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26869964599609375},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2005.1415119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.9416","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.9416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/78413/2005-deng-icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W185340767","https://openalex.org/W1516038907","https://openalex.org/W1549321558","https://openalex.org/W1561709555","https://openalex.org/W1633884584","https://openalex.org/W2159501365","https://openalex.org/W2160955451","https://openalex.org/W2161748486","https://openalex.org/W2168267625","https://openalex.org/W2465919943","https://openalex.org/W4253439942","https://openalex.org/W6607524910","https://openalex.org/W6719392674","https://openalex.org/W6835313328"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2994894110","https://openalex.org/W2048014685"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,111,176],"novel":[3],"acoustic":[4,50,80,101],"model":[5,55,75],"of":[6,29,32,36,54,72,85,98,161],"speech,":[7],"based":[8],"on":[9],"statistical":[10,70],"hidden":[11],"trajectory":[12],"modeling":[13],"(HTM)":[14],"with":[15,60,113,128],"bi-directional":[16],"vocal":[17],"tract":[18],"resonance":[19],"(VTR)":[20],"target":[21],"filtering,":[22],"for":[23],"speech":[24],"recognition.":[25],"The":[26],"HTM":[27,150],"consists":[28],"two":[30],"stages":[31],"the":[33,39,48,69,83,91,94,100,114,124,129,135,140,149,169],"generative":[34],"process":[35],"speech:":[37],"from":[38,144],"phone":[40],"sequence":[41],"to":[42,47,90,134,146],"VTR":[43,73,145],"dynamics":[44],"and":[45,64,77,127],"then":[46],"cepstrum-based":[49],"observation.":[51],"Two":[52],"types":[53],"implementation":[56],"are":[57,152],"detailed,":[58],"one":[59],"straightforward":[61],"two-stage":[62],"cascading,":[63],"another":[65],"which":[66],"integrates":[67],"over":[68,123],"distribution":[71],"in":[74,78,93,105,139,168],"construction":[76],"computing":[79],"likelihood.":[81],"With":[82],"use":[84],"first-order":[86],"Taylor":[87],"series":[88],"approximation":[89],"nonlinearity":[92],"VTR-to-cepstrum":[95],"prediction":[96],"component":[97],"HTM,":[99],"likelihood":[102],"is":[103,110,166],"established":[104],"an":[106,162],"analytical":[107],"form.":[108],"It":[109],"Gaussian":[112],"time-varying":[115],"mean":[116],"that":[117],"gives":[118],"structured":[119],"long-span":[120],"context":[121],"dependence":[122],"entire":[125],"utterance,":[126],"dynamically":[130],"adjusted":[131],"variance":[132],"proportional":[133],"squared":[136],"\"local":[137],"slope\"":[138],"nonlinear":[141],"mapping":[142],"function":[143],"cepstrum.":[147],"When":[148],"parameters":[151],"trained":[153],"via":[154],"maximizing":[155],"this":[156],"\"integrated\"":[157],"likelihood,":[158],"dramatic":[159],"reduction":[160],"upper":[163],"error":[164],"bound":[165],"achieved":[167],"standard":[170],"TIMIT":[171],"phonetic":[172],"recognition":[173],"task":[174],"using":[175],"large-scale":[177],"N-best":[178],"rescoring":[179],"paradigm.":[180]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}