{"id":"https://openalex.org/W2338186431","doi":"https://doi.org/10.1109/icassp.2016.7472757","title":"Directly modeling voiced and unvoiced components in speech waveforms by neural networks","display_name":"Directly modeling voiced and unvoiced components in speech waveforms by neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2338186431","doi":"https://doi.org/10.1109/icassp.2016.7472757","mag":"2338186431"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nitech.repo.nii.ac.jp/records/6222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Google","Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103023678"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":7.5379,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97188083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5640","last_page":"5644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9943000078201294,"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":0.9894000291824341,"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/waveform","display_name":"Waveform","score":0.823764443397522},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6548227071762085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6468762159347534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377881169319153},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5943422317504883},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5073327422142029},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.464703232049942},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4576086699962616},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4474411904811859},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4374561905860901},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4347638487815857},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.4344456195831299},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32195591926574707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3179294466972351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23095551133155823},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08671987056732178},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07061725854873657}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.823764443397522},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6548227071762085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6468762159347534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377881169319153},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5943422317504883},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5073327422142029},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.464703232049942},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4576086699962616},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4474411904811859},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4374561905860901},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4347638487815857},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.4344456195831299},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32195591926574707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3179294466972351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23095551133155823},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08671987056732178},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07061725854873657},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001438025","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/6222","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001438025","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/6222","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W233059834","https://openalex.org/W1522301498","https://openalex.org/W1527535554","https://openalex.org/W1576227399","https://openalex.org/W1600722501","https://openalex.org/W1904365287","https://openalex.org/W2009674825","https://openalex.org/W2035424729","https://openalex.org/W2057653135","https://openalex.org/W2063105057","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2133035145","https://openalex.org/W2136442985","https://openalex.org/W2146502635","https://openalex.org/W2285182995","https://openalex.org/W2293634267","https://openalex.org/W2395578248","https://openalex.org/W2964121744","https://openalex.org/W3142087749","https://openalex.org/W6631190155","https://openalex.org/W6640036494","https://openalex.org/W6675380101","https://openalex.org/W6679574054","https://openalex.org/W6681435938","https://openalex.org/W6696079272","https://openalex.org/W6696934422","https://openalex.org/W6711777497","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W4300066510","https://openalex.org/W1971337326","https://openalex.org/W2056958800","https://openalex.org/W4213259725","https://openalex.org/W4311388919","https://openalex.org/W1964490787","https://openalex.org/W2060696366"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,22,29,34,57],"novel":[4],"acoustic":[5],"model":[6],"based":[7],"on":[8],"neural":[9,17],"networks":[10],"for":[11],"statistical":[12],"parametric":[13],"speech":[14,35,58,78,82],"synthesis.":[15],"The":[16,40],"network":[18],"outputs":[19],"parameters":[20],"of":[21,33,45,56],"non-zero":[23],"mean":[24,41],"Gaussian":[25,47],"process,":[26],"which":[27],"defines":[28],"probability":[30],"density":[31],"function":[32],"waveform":[36],"given":[37],"linguistic":[38],"features.":[39],"and":[42,52],"covariance":[43],"functions":[44],"the":[46,61,65,73],"process":[48],"represent":[49],"deterministic":[50],"(voiced)":[51],"stochastic":[53],"(unvoiced)":[54],"components":[55],"waveform,":[59],"whereas":[60],"previous":[62],"approach":[63,75],"considered":[64],"unvoiced":[66],"component":[67],"only.":[68],"Experimental":[69],"results":[70],"show":[71],"that":[72],"proposed":[74],"can":[76],"generate":[77],"waveforms":[79],"approximating":[80],"natural":[81],"waveforms.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}