{"id":"https://openalex.org/W2099352211","doi":"https://doi.org/10.1109/icassp.2012.6288799","title":"Modeling pitch trajectory by hierarchical HMM with minimum generation error training","display_name":"Modeling pitch trajectory by hierarchical HMM with minimum generation error training","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2099352211","doi":"https://doi.org/10.1109/icassp.2012.6288799","mag":"2099352211"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039492028","display_name":"Yi-Jian Wu","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/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Speech Group, Microsoft Research Asia, Beijing, China","[Speech Group, Microsoft Research Asia, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Speech Group, Microsoft Research Asia, Beijing, China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"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/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Speech Group, Microsoft Research Asia, Beijing, China","[Speech Group, Microsoft Research Asia, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Speech Group, Microsoft Research Asia, Beijing, China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4228,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94473251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4017","last_page":"4020"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.763506293296814},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7285101413726807},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6987862586975098},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6188089847564697},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.49157437682151794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47933587431907654},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45471760630607605},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4495483934879303},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4309016466140747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858819305896759},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3661157488822937},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3643878698348999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15796062350273132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763506293296814},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7285101413726807},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6987862586975098},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6188089847564697},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.49157437682151794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47933587431907654},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45471760630607605},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4495483934879303},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4309016466140747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858819305896759},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3661157488822937},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3643878698348999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15796062350273132},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W4362787","https://openalex.org/W35069904","https://openalex.org/W59470279","https://openalex.org/W69946184","https://openalex.org/W128185859","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W1993523973","https://openalex.org/W2106632010","https://openalex.org/W2108674328","https://openalex.org/W2111194146","https://openalex.org/W2144139079","https://openalex.org/W2166823384","https://openalex.org/W2168531172","https://openalex.org/W2740537351","https://openalex.org/W3036802551","https://openalex.org/W6601467884","https://openalex.org/W6602870314","https://openalex.org/W6605245121","https://openalex.org/W6676044216","https://openalex.org/W6676358011","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W3145575561","https://openalex.org/W2164162849","https://openalex.org/W3200375535"],"abstract_inverted_index":{"A":[0],"hierarchical":[1,23,91],"pitch":[2,14],"model":[3,41,54],"(HPM)":[4],"was":[5],"recently":[6],"proposed":[7],"to":[8,39,51,57,79,107],"HMM-based":[9],"speech":[10],"synthesis.":[11],"In":[12,43],"HPM,":[13],"trajectory":[15,110],"is":[16,37],"modeled":[17],"as":[18],"an":[19],"additive":[20],"combination":[21],"of":[22,83],"layers":[24],"(including":[25],"state,":[26],"phone,":[27],"syllable,":[28],"etc),":[29],"and":[30,66,89],"a":[31,52,68],"minimum":[32],"generation":[33],"error":[34],"(MGE)":[35],"criterion":[36,50],"used":[38],"re-estimate":[40],"parameters.":[42],"this":[44],"paper,":[45],"we":[46],"extend":[47],"the":[48,60,81,98,114,125],"MGE":[49,70,100],"tree-based":[53],"clustering":[55],"process":[56,72],"simultaneously":[58],"cluster":[59],"context-dependent":[61],"models":[62],"at":[63],"all":[64],"layers,":[65],"construct":[67],"full":[69,99],"training":[71,87,101],"for":[73],"HPM":[74,84,122],"training.":[75],"Experiments":[76],"were":[77],"conducted":[78],"investigate":[80],"effects":[82],"with":[85],"different":[86,90],"criteria":[88],"layer":[92],"combinations.":[93],"Experimental":[94],"results":[95],"show":[96],"that":[97],"can":[102],"significantly":[103],"improve":[104],"HPM's":[105],"ability":[106],"predict":[108],"F0":[109,130],"in":[111,129],"TTS":[112],"over":[113],"ML-based":[115],"approach":[116],"on":[117],"test":[118],"data.":[119],"The":[120],"new":[121],"also":[123],"outperforms":[124],"conventional":[126],"state-level":[127],"HMM":[128],"prediction.":[131]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}