{"id":"https://openalex.org/W2050675057","doi":"https://doi.org/10.1109/icassp.2014.6855144","title":"Improvement of Probabilistic Acoustic Tube model for speech decomposition","display_name":"Improvement of Probabilistic Acoustic Tube model for speech decomposition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2050675057","doi":"https://doi.org/10.1109/icassp.2014.6855144","mag":"2050675057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Yang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign","Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, , USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign","Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Illinois, Urbana, IL, , USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"7929","last_page":"7933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9994000196456909,"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":0.8741358518600464},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6734371185302734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665662527084351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6527813673019409},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5819661021232605},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48159050941467285},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46777787804603577},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4473596215248108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43451637029647827},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41643762588500977},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4069816768169403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19643330574035645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15286436676979065},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09600073099136353},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07308891415596008}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8741358518600464},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6734371185302734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665662527084351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6527813673019409},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5819661021232605},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48159050941467285},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46777787804603577},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4473596215248108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43451637029647827},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41643762588500977},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4069816768169403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19643330574035645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15286436676979065},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09600073099136353},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07308891415596008}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6855144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.5392","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.5392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isle.illinois.edu/sst/pubs/2014/zhang14.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W169745891","https://openalex.org/W1557133539","https://openalex.org/W1766888123","https://openalex.org/W1881757884","https://openalex.org/W1886421314","https://openalex.org/W1926440348","https://openalex.org/W2022194925","https://openalex.org/W2025920047","https://openalex.org/W2045559754","https://openalex.org/W2131062138","https://openalex.org/W2155505023","https://openalex.org/W2157240849","https://openalex.org/W2157328787","https://openalex.org/W2158881414","https://openalex.org/W2478884216","https://openalex.org/W6639375475","https://openalex.org/W6640445917"],"related_works":["https://openalex.org/W2020989338","https://openalex.org/W1823617068","https://openalex.org/W2147126679","https://openalex.org/W4300049944","https://openalex.org/W2115039802","https://openalex.org/W1546240199","https://openalex.org/W2400533375","https://openalex.org/W193702574","https://openalex.org/W2470236000","https://openalex.org/W642007152"],"abstract_inverted_index":{"Current":[0],"model-based":[1],"speech":[2,51,127,135],"analysis":[3,49],"tends":[4],"to":[5,103],"be":[6,32,54],"incomplete":[7],"-":[8],"only":[9,17],"a":[10,66],"part":[11],"of":[12,14,43,88],"parameters":[13,44,52,130],"interest":[15],"(e.g.":[16],"the":[18,26,48],"pitch":[19],"or":[20,56],"vocal":[21,75],"tract)":[22],"are":[23,34,46,79,99],"modeled,":[24],"while":[25],"rest":[27],"that":[28,39,45],"might":[29],"as":[30],"well":[31],"important":[33],"disregarded.":[35],"The":[36],"drawback":[37],"is":[38,107],"without":[40],"joint":[41],"modeling":[42,98],"correlated,":[47],"on":[50],"may":[53],"inaccurate":[55],"even":[57],"incorrect.":[58],"Under":[59],"this":[60],"motivation,":[61],"we":[62],"have":[63],"proposed":[64],"such":[65],"model":[67],"called":[68],"PAT":[69,89],"(Probabilistic":[70],"Acoustic":[71],"Tube),":[72],"where":[73,93],"pitch,":[74],"tract":[76],"and":[77,96,117,131],"energy":[78],"jointly":[80],"modeled.":[81],"This":[82],"paper":[83],"proposes":[84],"an":[85],"improved":[86],"version":[87],"model,":[90],"named":[91],"PAT2,":[92],"both":[94],"signal":[95],"probabilistic":[97],"tremendously":[100],"renovated.":[101],"Compared":[102],"related":[104],"works,":[105],"PAT2":[106],"much":[108],"more":[109],"comprehensive,":[110],"which":[111],"incorporates":[112],"mixed":[113],"excitation,":[114],"glottal":[115],"wave":[116],"phase":[118],"modeling.":[119],"Experimental":[120],"results":[121],"show":[122],"its":[123,132],"ability":[124],"in":[125],"decomposing":[126],"into":[128],"desirable":[129],"potential":[133],"for":[134],"synthesis.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}