{"id":"https://openalex.org/W2067549749","doi":"https://doi.org/10.1109/iscslp.2014.6936598","title":"Improving F0 prediction using bidirectional associative memories and syllable-level F0 features for HMM-based Mandarin speech synthesis","display_name":"Improving F0 prediction using bidirectional associative memories and syllable-level F0 features for HMM-based Mandarin speech synthesis","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2067549749","doi":"https://doi.org/10.1109/iscslp.2014.6936598","mag":"2067549749"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th 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/A5011189832","display_name":"Gao Li","orcid":"https://orcid.org/0000-0003-1171-9179"},"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 Gao","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"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":"Ling-Hui Chen","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, 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":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, 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":0.6203,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67869832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"279"},"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":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8787274360656738},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8142160177230835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7596888542175293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460372447967529},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6466373801231384},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5637120008468628},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5543060302734375},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44808781147003174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43299782276153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197652339935303},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41746050119400024}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8787274360656738},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8142160177230835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7596888542175293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460372447967529},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6466373801231384},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5637120008468628},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5543060302734375},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44808781147003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43299782276153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197652339935303},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41746050119400024},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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.2014.6936598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W59470279","https://openalex.org/W1600722501","https://openalex.org/W1995118599","https://openalex.org/W2049686551","https://openalex.org/W2095425517","https://openalex.org/W2109938215","https://openalex.org/W2111194146","https://openalex.org/W2116064496","https://openalex.org/W2126289105","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2161736993","https://openalex.org/W2168531172","https://openalex.org/W3142087749","https://openalex.org/W4301420498","https://openalex.org/W6676358011"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W4391272374","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"The":[0],"speech":[1,9,69],"generated":[2],"by":[3,95,106],"hidden":[4],"Markov":[5],"model":[6],"(HMM)":[7],"based":[8,112],"synthesis":[10,70],"method":[11,60,123],"always":[12],"sounds":[13],"monotonous":[14],"compared":[15],"with":[16],"natural":[17,104],"recordings.":[18],"An":[19],"important":[20],"reason":[21],"is":[22],"that":[23,118],"the":[24,33,40,49,63,91,96,119,134],"predicted":[25,94],"F0":[26,37,51,64,76,92,121],"trajectories":[27,93],"are":[28,88,101],"over-smoothed.":[29],"This":[30],"arises":[31],"from":[32,90],"adoption":[34],"of":[35,43,66,136],"frame-level":[36],"features":[38,100],"and":[39],"averaging":[41],"effect":[42],"acoustic":[44],"modeling":[45,52],"using":[46,124,150],"Gaussians":[47],"in":[48,71],"conventional":[50,97],"approach.":[53,98],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,72],"to":[61],"improve":[62,133],"prediction":[65],"HMM-based":[67],"Mandarin":[68],"post-filtering":[73,122,144],"way.":[74],"Syllable-level":[75],"features,":[77],"e.g.,":[78],"length-normalized":[79],"logF0":[80,126,141],"vectors":[81,127,142],"or":[82,128],"quantitative":[83],"target":[84],"approximation":[85],"(qTA)":[86],"parameters,":[87],"extracted":[89],"These":[99],"mapped":[102],"towards":[103],"ones":[105],"Gaussian":[107],"bidirectional":[108],"associative":[109],"memory":[110],"(GBAM)":[111],"transformation.":[113],"Our":[114],"subjective":[115],"experiments":[116],"indicate":[117],"GBAM-based":[120],"either":[125],"qTA":[129,152],"parameters":[130],"can":[131,145],"significantly":[132],"naturalness":[135],"synthetic":[137],"speech.":[138],"Using":[139],"raw":[140],"for":[143],"achieve":[146],"better":[147],"performance":[148],"than":[149],"derived":[151],"parameters.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}