{"id":"https://openalex.org/W2398940758","doi":"https://doi.org/10.21437/ssw.2016-36","title":"Using instantaneous frequency and aperiodicity detection to estimate F0 for high-quality speech synthesis","display_name":"Using instantaneous frequency and aperiodicity detection to estimate F0 for high-quality speech synthesis","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2398940758","doi":"https://doi.org/10.21437/ssw.2016-36","mag":"2398940758"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1605.07809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hideki Kawahara","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hideki Kawahara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yannis Agiomyrgiannakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Agiomyrgiannakis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Heiga Zen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.092,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92856983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9986000061035156,"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":0.9965999722480774,"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/instantaneous-phase","display_name":"Instantaneous phase","score":0.7254999876022339},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6305999755859375},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6092000007629395},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5791000127792358},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5248000025749207},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.45899999141693115}],"concepts":[{"id":"https://openalex.org/C137798554","wikidata":"https://www.wikidata.org/wiki/Q6038852","display_name":"Instantaneous phase","level":3,"score":0.7254999876022339},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5318999886512756},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5248000025749207},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C44682112","wikidata":"https://www.wikidata.org/wiki/Q918242","display_name":"Low-pass filter","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3596000075340271},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C147788027","wikidata":"https://www.wikidata.org/wiki/Q2718101","display_name":"Band-pass filter","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2016-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1605.07809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07809","pdf_url":"https://arxiv.org/pdf/1605.07809","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1605.07809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07809","pdf_url":"https://arxiv.org/pdf/1605.07809","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,101],"paper":[1],"introduces":[2],"a":[3,59,88,94,107],"general":[4],"and":[5,10,23,36,43,46,98,124,126],"flexible":[6],"framework":[7,28,55],"for":[8,19],"F0":[9,40,44,67,71,79],"aperiodicity":[11,38,47,84,104],"(additive":[12],"non":[13],"periodic":[14],"component)":[15],"analysis,":[16],"specifically":[17],"intended":[18],"high-quality":[20],"speech":[21],"synthesis":[22],"modification":[24],"applications.":[25],"The":[26,81,116],"proposed":[27,54],"consists":[29,86],"of":[30,52,61,65,76,87],"three":[31],"subsystems:":[32],"instantaneous":[33],"frequency":[34],"estimator":[35],"initial":[37],"detector,":[39],"trajectory":[41],"tracker,":[42],"refinement":[45],"extractor.":[48],"A":[49],"preliminary":[50],"implementation":[51],"the":[53,112,130],"substantially":[56],"outperformed":[57],"(by":[58],"factor":[60],"10":[62],"in":[63,73],"terms":[64],"RMS":[66],"estimation":[68],"error)":[69],"existing":[70],"extractors":[72],"tracking":[74],"ability":[75],"temporally":[77],"varying":[78],"trajectories.":[80],"front":[82,102],"end":[83,103],"detector":[85,105],"complex-valued":[89],"wavelet":[90],"analysis":[91],"filter":[92],"with":[93,129],"highly":[95],"selective":[96],"temporal":[97],"spectral":[99],"envelope.":[100],"uses":[106],"new":[108],"measure":[109,117],"that":[110],"quantifies":[111],"deviation":[113],"from":[114],"periodicity.":[115],"is":[118],"less":[119],"sensitive":[120],"to":[121,132],"slow":[122],"FM":[123],"AM":[125],"closely":[127],"correlates":[128],"signal":[131],"noise":[133],"ratio.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-22T06:01:30.510260","created_date":"2016-06-24T00:00:00"}