{"id":"https://openalex.org/W2748379347","doi":"https://doi.org/10.21437/interspeech.2017-1288","title":"Generative Adversarial Network-Based Glottal Waveform Model for Statistical Parametric Speech Synthesis","display_name":"Generative Adversarial Network-Based Glottal Waveform Model for Statistical Parametric Speech Synthesis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748379347","doi":"https://doi.org/10.21437/interspeech.2017-1288","mag":"2748379347"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1288","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.05955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064828339","display_name":"Bajibabu Bollepalli","orcid":"https://orcid.org/0000-0003-1268-0579"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Bajibabu Bollepalli","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064828339"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":6.2773,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97086843,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3394","last_page":"3398"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.7555663585662842},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7429304122924805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6452851295471191},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6265020370483398},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5148417353630066},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.46760857105255127},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4329681098461151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4247836470603943},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4143028259277344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4069027304649353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16880619525909424},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07008710503578186},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06428992748260498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555663585662842},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7429304122924805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6452851295471191},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6265020370483398},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5148417353630066},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.46760857105255127},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4329681098461151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4247836470603943},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4143028259277344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4069027304649353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16880619525909424},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07008710503578186},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06428992748260498},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1288","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.05955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05955","pdf_url":"https://arxiv.org/pdf/1903.05955","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"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/28868","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/d46f19a6-879f-41b9-9142-032ba6e624ab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.05955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05955","pdf_url":"https://arxiv.org/pdf/1903.05955","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1529628403","https://openalex.org/W1576227399","https://openalex.org/W1630569004","https://openalex.org/W1836465849","https://openalex.org/W1963637322","https://openalex.org/W2021320575","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2099076569","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2110420312","https://openalex.org/W2111284386","https://openalex.org/W2115846934","https://openalex.org/W2125389028","https://openalex.org/W2129082420","https://openalex.org/W2129142580","https://openalex.org/W2173520492","https://openalex.org/W2294797155","https://openalex.org/W2395578248","https://openalex.org/W2398742733","https://openalex.org/W2405614646","https://openalex.org/W2406017614","https://openalex.org/W2417163358","https://openalex.org/W2519091744","https://openalex.org/W2586183200","https://openalex.org/W2591927543","https://openalex.org/W2593414223","https://openalex.org/W2594809597","https://openalex.org/W2595110011","https://openalex.org/W2658996865","https://openalex.org/W2666408839","https://openalex.org/W2748692141","https://openalex.org/W2808342999","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2949496494","https://openalex.org/W2963684088","https://openalex.org/W2963828919","https://openalex.org/W2964281804","https://openalex.org/W3123963976","https://openalex.org/W4301202368","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2020989338","https://openalex.org/W1823617068","https://openalex.org/W2147126679","https://openalex.org/W4300049944","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2115039802","https://openalex.org/W2039489009","https://openalex.org/W2047528018"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,19,31,111,173,183],"text-to-speech":[5],"synthesis":[6,179],"quality":[7,180],"can":[8],"be":[9],"improved":[10],"by":[11,47,102,132,142,165],"using":[12,48,161,188],"glottal":[13,26,40,44,61,100,139,151,162],"vocoding.":[14],"This":[15],"refers":[16],"to":[17,66,73,113,129,149,182],"vocoders":[18,41],"parameterize":[20],"speech":[21,36,159],"into":[22],"two":[23],"parts,":[24],"the":[25,34,43,54,59,75,79,115,130,135,174],"excitation":[27,45,62],"and":[28,168],"vocal":[29],"tract,":[30],"occur":[32],"in":[33,118],"human":[35],"production":[37],"apparatus.":[38],"Current":[39],"generate":[42],"waveform":[46],"deep":[49],"neural":[50],"networks":[51,105],"(DNNs).":[52],"However,":[53],"squared":[55],"error-based":[56],"training":[57],"of":[58,78,124,184],"present":[60],"models":[63,110],"is":[64,86],"limited":[65],"generating":[67],"conditional":[68],"average":[69],"waveforms,":[70],"which":[71],"fails":[72],"capture":[74],"stochastic":[76,146],"variation":[77],"waveforms.":[80],"As":[81],"a":[82,95,119,145],"result,":[83],"shaped":[84],"noise":[85,191],"added":[87],"as":[88],"post-processing.":[89],"In":[90,153],"this":[91],"study,":[92],"we":[93,156],"propose":[94],"new":[96,125],"method":[97],"for":[98],"predicting":[99],"waveforms":[101,163],"generative":[103,109],"adversarial":[104],"(GANs).":[106],"GANs":[107,143,177],"are":[108],"aim":[112],"embed":[114],"data":[116],"distribution":[117],"latent":[120,136],"space,":[121],"enabling":[122],"generation":[123],"instances":[126],"very":[127],"similar":[128,148],"original":[131],"randomly":[133],"sampling":[134],"distribution.":[137],"The":[138,170],"pulses":[140],"generated":[141,160],"show":[144,172],"component":[147],"natural":[150],"pulses.":[152],"our":[154],"experiments,":[155],"compare":[157],"synthetic":[158],"produced":[164],"both":[166],"DNNs":[167],"GANs.":[169],"results":[171],"newly":[175],"proposed":[176],"achieve":[178],"comparable":[181],"widely-used":[185],"DNNs,":[186],"without":[187],"an":[189],"additive":[190],"component.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2017-08-31T00:00:00"}