{"id":"https://openalex.org/W2165544306","doi":"https://doi.org/10.1109/icassp.2004.1326046","title":"A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances","display_name":"A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2165544306","doi":"https://doi.org/10.1109/icassp.2004.1326046","mag":"2165544306"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5067818713","display_name":"Li Deng","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":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/A5073098279","display_name":"L.J. Lee","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":"L.J. Lee","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/A5110453625","display_name":"Hagai Attias","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":"H. Attias","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/A5067818713"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.9997,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.94171715,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8980231881141663},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6643325686454773},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6572310328483582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6510552167892456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6373008489608765},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5314342975616455},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.521296501159668},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.44295981526374817},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4119677245616913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3238353729248047},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28544706106185913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19945964217185974},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.10179275274276733}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8980231881141663},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6643325686454773},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6572310328483582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6510552167892456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373008489608765},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5314342975616455},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.521296501159668},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.44295981526374817},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4119677245616913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3238353729248047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28544706106185913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19945964217185974},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.10179275274276733},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326046","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.3317","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.3317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.goldenmetallic.com/icassp04_li.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.4590","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.4590","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/srg/papers/2004-deng-icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1047238","https://openalex.org/W185340767","https://openalex.org/W1527878980","https://openalex.org/W1560505509","https://openalex.org/W1990394889","https://openalex.org/W2064758410","https://openalex.org/W2092684968","https://openalex.org/W2104298309","https://openalex.org/W2125956490","https://openalex.org/W2135034868","https://openalex.org/W2161748486","https://openalex.org/W2161925948","https://openalex.org/W4285719527","https://openalex.org/W6600037722","https://openalex.org/W6607524910","https://openalex.org/W6631574769","https://openalex.org/W6678492994"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2045900265","https://openalex.org/W2131046383"],"abstract_inverted_index":{"A":[0],"novel":[1],"approach":[2,135],"is":[3,31,85],"developed":[4],"for":[5,73],"efficient":[6],"and":[7,46,54,68,87,95],"accurate":[8],"tracking":[9,29,83,108],"of":[10,18,36,42,62,127],"vocal":[11,109],"tract":[12,110],"resonances,":[13],"which":[14],"are":[15],"natural":[16],"frequencies":[17,53],"the":[19,37,63,74,78,92,96,120,125,132,152],"resonator":[20],"from":[21,51,137],"larynx":[22],"to":[23,56],"lips,":[24],"in":[25,100,112,119,131,141,160],"fluent":[26],"speech.":[27],"The":[28],"algorithm":[30,84],"based":[32],"on":[33,107],"a":[34,47],"version":[35],"structured":[38],"speech":[39,114,161],"model":[40],"consisting":[41],"continuous-valued":[43],"hidden":[44],"dynamics":[45],"piecewise-linearized":[48],"prediction":[49,79],"function":[50],"resonance":[52],"bandwidths":[55],"LPC":[57],"cepstra.":[58],"We":[59],"present":[60],"details":[61],"piecewise":[64,97],"linearization":[65,98],"design":[66,99],"process":[67],"an":[69,101],"adaptive":[70,102],"training":[71,94,129],"technique":[72],"parameters":[75],"that":[76,89,142],"characterize":[77],"residuals.":[80],"An":[81],"iterative":[82],"described":[86],"evaluated":[88],"embeds":[90],"both":[91],"prediction-residual":[93],"Kalman":[103],"filtering":[104],"framework.":[105],"Experiments":[106],"resonances":[111],"Switchboard":[113],"data":[115],"demonstrate":[116],"high":[117],"accuracy":[118],"results,":[121],"as":[122,124],"well":[123],"effectiveness":[126],"residual":[128],"embedded":[130],"algorithm.":[133],"Our":[134],"differs":[136],"traditional":[138],"formant":[139],"trackers":[140],"it":[143],"provides":[144],"meaningful":[145],"results":[146],"even":[147],"during":[148],"consonantal":[149],"closures":[150],"when":[151],"supra-laryngeal":[153],"source":[154],"may":[155],"cause":[156],"no":[157],"spectral":[158],"prominences":[159],"acoustics.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}