{"id":"https://openalex.org/W1603639024","doi":"https://doi.org/10.1109/icassp.2003.1198920","title":"Variational inference and learning for segmental switching state space models of hidden speech dynamics","display_name":"Variational inference and learning for segmental switching state space models of hidden speech dynamics","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1603639024","doi":"https://doi.org/10.1109/icassp.2003.1198920","mag":"1603639024"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198920","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5036935290","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"]},{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA","US"],"is_corresponding":true,"raw_author_name":"L.J. Lee","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Waterloo, Waterloo, ONT, Canada","Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Waterloo, Waterloo, ONT, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Microsoft Research Limited, 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/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":["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":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036935290"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":3.1093,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92548435,"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":"872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9975000023841858,"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":0.9567000269889832,"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/inference","display_name":"Inference","score":0.7436805963516235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7085719108581543},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6018748879432678},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5326476097106934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5095481872558594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48095980286598206},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47761863470077515},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44737258553504944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24202418327331543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.174144446849823},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12736964225769043},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08685556054115295}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7436805963516235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085719108581543},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6018748879432678},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5326476097106934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5095481872558594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48095980286598206},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47761863470077515},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44737258553504944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24202418327331543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.174144446849823},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12736964225769043},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08685556054115295},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1198920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198920","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.2885","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.2885","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/icassp03_sss.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W185340767","https://openalex.org/W1485628714","https://openalex.org/W1504777792","https://openalex.org/W1647559354","https://openalex.org/W1873628625","https://openalex.org/W1912842243","https://openalex.org/W1947921031","https://openalex.org/W1978809497","https://openalex.org/W2005054044","https://openalex.org/W2068703228","https://openalex.org/W2083393647","https://openalex.org/W2092684968","https://openalex.org/W2102716594","https://openalex.org/W2105162697","https://openalex.org/W2118825896","https://openalex.org/W2122994642","https://openalex.org/W2125107595","https://openalex.org/W2148812765","https://openalex.org/W2170463421","https://openalex.org/W2963725131","https://openalex.org/W6607524910","https://openalex.org/W6637345020"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W1986418932","https://openalex.org/W2156919374","https://openalex.org/W35446969","https://openalex.org/W1984019423","https://openalex.org/W4280588203"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"novel":[3],"and":[4,52,65,82,88,113,121,141],"powerful":[5,64],"variational":[6,93],"EM":[7],"algorithms":[8,69,115,133],"for":[9,109,116],"the":[10,61,73,105,132],"segmental":[11,106],"switching":[12],"state":[13],"space":[14],"models":[15,36,46],"used":[16],"in":[17],"speech":[18,32,111,119,123,143],"applications,":[19],"which":[20],"are":[21,90,135],"capable":[22],"of":[23,30,43,57,63,72,131],"capturing":[24],"key":[25],"internal":[26],"(or":[27],"hidden)":[28],"dynamics":[29,112,120],"natural":[31],"production.":[33],"Hidden":[34],"dynamic":[35],"(HDMs)":[37],"have":[38,103],"recently":[39],"become":[40],"a":[41,92],"class":[42],"promising":[44],"acoustic":[45,126],"to":[47,97],"incorporate":[48],"crucial":[49,108],"speech-specific":[50],"knowledge":[51],"overcome":[53],"many":[54],"inherent":[55],"weaknesses":[56],"traditional":[58],"HMMs.":[59],"However,":[60],"lack":[62],"efficient":[66],"statistical":[67],"learning":[68,89],"is":[70,95],"one":[71],"main":[74],"obstacles":[75],"preventing":[76],"them":[77],"from":[78,125],"being":[79],"well":[80],"studied":[81],"widely":[83],"used.":[84],"Since":[85],"exact":[86],"inference":[87],"intractable,":[91],"approach":[94],"taken":[96],"develop":[98],"effective":[99],"approximate":[100],"algorithms.":[101],"We":[102],"implemented":[104],"constraint":[107],"modeling":[110],"present":[114],"recovering":[117],"hidden":[118],"discrete":[122],"units":[124],"data":[127],"only.":[128],"The":[129],"effectiveness":[130],"developed":[134],"verified":[136],"by":[137],"experiments":[138],"on":[139],"simulation":[140],"Switchboard":[142],"data.":[144]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}