{"id":"https://openalex.org/W2144317449","doi":"https://doi.org/10.1109/iscslp.2010.5684833","title":"Statistical modeling of syllable-level F0 features for HMM-based unit selection speech synthesis","display_name":"Statistical modeling of syllable-level F0 features for HMM-based unit selection speech synthesis","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2144317449","doi":"https://doi.org/10.1109/iscslp.2010.5684833","mag":"2144317449"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430099","display_name":"Zhiguo Wang","orcid":"https://orcid.org/0000-0003-3686-6220"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Guo Wang","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFLYTEK Speech Lab, Univ. of Sci. & Technol. of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"147"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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/T12031","display_name":"Speech and dialogue systems","score":0.9919000267982483,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8842529058456421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7822743654251099},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7167536616325378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920589804649353},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.566321849822998},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5500364899635315},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5317816734313965},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4848412275314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496321678161621},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4453406035900116},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4223601520061493},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4191182851791382},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.410104364156723}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8842529058456421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7822743654251099},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7167536616325378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920589804649353},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.566321849822998},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5500364899635315},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5317816734313965},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4848412275314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496321678161621},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4453406035900116},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4223601520061493},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4191182851791382},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.410104364156723},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1963627370","https://openalex.org/W1973766695","https://openalex.org/W2093450784","https://openalex.org/W2131958409","https://openalex.org/W2147868561","https://openalex.org/W2150658333","https://openalex.org/W2159528802","https://openalex.org/W2166823384","https://openalex.org/W2168531172","https://openalex.org/W2394761397","https://openalex.org/W2403351921","https://openalex.org/W6679513055","https://openalex.org/W6683640347","https://openalex.org/W6711946264","https://openalex.org/W6713743917"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2038801705","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2024201202","https://openalex.org/W2535215250","https://openalex.org/W2049083033"],"abstract_inverted_index":{"In":[0],"current":[1,53],"hidden":[2],"Markov":[3],"model(HMM)":[4],"based":[5],"unit":[6,102,113,124],"selection":[7,103,125],"speech":[8,165],"synthesis":[9],"method,":[10],"the":[11,19,24,34,46,52,55,59,74,92,101,107,122,132,135,139,148,161],"optimal":[12],"phone-sized":[13,123],"candidate":[14,136],"units":[15,137],"are":[16,70],"selected":[17],"following":[18],"maximum":[20],"likelihood(ML)":[21],"criterion":[22,104],"of":[23,58,77,95,110,141,163],"HMMs":[25],"trained":[26,85],"for":[27,37,67,121,138],"various":[28],"acoustic":[29],"features.":[30,79],"This":[31],"paper":[32],"introduces":[33],"statistical":[35,82],"models":[36],"syllable-level":[38,88,149],"F0":[39,48,78,89,150],"features":[40,90],"into":[41,100,130],"this":[42,96,157],"method.":[43],"Different":[44],"from":[45],"frame-level":[47],"parameters":[49],"used":[50],"in":[51,61],"framework,":[54],"pitch":[56],"contour":[57],"vowel":[60],"each":[62],"syllable":[63],"and":[64,91],"its":[65],"combination":[66],"adjacent":[68,142],"syllables":[69,143],"extracted":[71],"to":[72,105,128],"represent":[73],"suprasegmental":[75,108],"property":[76],"A":[80],"context-dependent":[81],"model":[83,97],"is":[84,98,126,145],"using":[86],"these":[87],"likelihood":[93],"function":[94],"integrated":[99],"evaluate":[106],"prosody":[109],"a":[111],"given":[112],"sequence.":[114],"The":[115],"conventional":[116],"dynamic":[117],"programming":[118],"search":[119],"algorithm":[120],"modified":[127],"take":[129],"account":[131],"dependency":[133],"between":[134],"vowels":[140],"which":[144],"caused":[146],"by":[147],"modeling.":[151],"Our":[152],"experiment":[153],"results":[154],"prove":[155],"that":[156],"method":[158],"can":[159],"improve":[160],"naturalness":[162],"synthesized":[164],"significantly.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}