{"id":"https://openalex.org/W2404851130","doi":"https://doi.org/10.21437/interspeech.2012-140","title":"Hidden Markov convolutive mixture model for pitch contour analysis of speech","display_name":"Hidden Markov convolutive mixture model for pitch contour analysis of speech","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2404851130","doi":"https://doi.org/10.21437/interspeech.2012-140","mag":"2404851130"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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":"https://openalex.org/A5047968682","display_name":"Kota Yoshizato","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kota Yoshizato","raw_affiliation_strings":["Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sagayama","raw_affiliation_strings":["Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"390","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.972100019454956,"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":0.972100019454956,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9693999886512756,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9125999808311462,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7537015080451965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7056540846824646},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.5619447827339172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5076178312301636},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.45754238963127136},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4559533894062042},{"id":"https://openalex.org/keywords/stochastic-modelling","display_name":"Stochastic modelling","score":0.4551326334476471},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4437764883041382},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.43581125140190125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42059171199798584},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4105134904384613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3833019733428955},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3498879671096802},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.24625107645988464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2221280038356781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20605605840682983},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.1663101315498352},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13573211431503296}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7537015080451965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056540846824646},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.5619447827339172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5076178312301636},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.45754238963127136},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4559533894062042},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.4551326334476471},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4437764883041382},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.43581125140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42059171199798584},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4105134904384613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3833019733428955},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3498879671096802},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.24625107645988464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2221280038356781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20605605840682983},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.1663101315498352},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13573211431503296}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-140","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.8817","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.8817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.brl.ntt.co.jp/people/kameoka/publications/Yoshizato2012Interspeech09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1849169576","https://openalex.org/W1965255698","https://openalex.org/W2034277951","https://openalex.org/W2071399124","https://openalex.org/W2131118158","https://openalex.org/W2321061684","https://openalex.org/W2396093700","https://openalex.org/W2397931447","https://openalex.org/W3041908733"],"related_works":["https://openalex.org/W2382132287","https://openalex.org/W2161328464","https://openalex.org/W2738224259","https://openalex.org/W3113307220","https://openalex.org/W2379333870","https://openalex.org/W1510894296","https://openalex.org/W2095453601","https://openalex.org/W4385889111","https://openalex.org/W2604015228","https://openalex.org/W1985514205"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,33,43,95],"stochastic":[4,13,23],"model":[5,40,59,98],"of":[6,15,71,76],"speech":[7,63,84,103],"F0":[8,45,57,104],"contours,":[9,105],"based":[10],"on":[11],"the":[12,16,22,38,51,55,69],"formulation":[14,24],"Fujisaki":[17,39,97,108],"model.":[18],"Our":[19],"motivation":[20],"for":[21,36],"is":[25],"twofold.":[26],"Firstly,":[27],"it":[28,48],"allows":[29],"us":[30],"to":[31,53,94],"derive":[32],"well-behaved":[34],"algorithm":[35,114],"estimating":[37],"parameters":[41],"from":[42],"raw":[44],"contour.":[46],"Secondly,":[47],"will":[49],"open":[50],"door":[52],"incorporating":[54],"well-founded":[56],"contour":[58],"into":[60],"various":[61],"statistical":[62,106],"processing":[64],"problems.":[65],"We":[66],"quantitatively":[67],"evaluated":[68],"performance":[70],"our":[72,90],"method":[73,91],"in":[74],"terms":[75],"an":[77],"Fujisaki-model":[78],"parameter":[79,99],"estimation":[80],"accuracy":[81],"using":[82],"real":[83],"data.":[85],"Experimental":[86],"results":[87],"revealed":[88],"that":[89],"was":[92],"superior":[93],"state-of-the-art":[96],"extractor.":[100],"Index":[101],"Terms:":[102],"model,":[107,109,112],"hidden":[110],"Markov":[111],"EM":[113]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}