{"id":"https://openalex.org/W2417163358","doi":"https://doi.org/10.21437/interspeech.2016-342","title":"GlottDNN \u2014 A Full-Band Glottal Vocoder for Statistical Parametric Speech Synthesis","display_name":"GlottDNN \u2014 A Full-Band Glottal Vocoder for Statistical Parametric Speech Synthesis","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2417163358","doi":"https://doi.org/10.21437/interspeech.2016-342","mag":"2417163358"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/728b2d17-5a83-41c7-987d-9a040119a491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013722514","display_name":"Manu Airaksinen","orcid":"https://orcid.org/0000-0002-8031-2260"},"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":"Manu Airaksinen","raw_affiliation_strings":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","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":false,"raw_author_name":"Bajibabu Bollepalli","raw_affiliation_strings":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","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":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]},{"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":["Aalto Univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto Univ","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2473","last_page":"2477"},"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":0.9977999925613403,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8012211322784424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7358670830726624},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6742895245552063},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5886138677597046},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5177137851715088},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.482991099357605},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.424099862575531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2911379337310791},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08362880349159241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012211322784424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7358670830726624},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6742895245552063},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5886138677597046},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5177137851715088},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.482991099357605},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.424099862575531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2911379337310791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08362880349159241},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/728b2d17-5a83-41c7-987d-9a040119a491","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/728b2d17-5a83-41c7-987d-9a040119a491","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Airaksinen, M, Bollepalli, B, Juvela, L, Wu, Z, King, S & Alku, P 2016, 'GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis', Paper presented at Interspeech 2016, San Francisco, United States, 8/09/16 - 12/09/16.","raw_type":"conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/728b2d17-5a83-41c7-987d-9a040119a491","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/728b2d17-5a83-41c7-987d-9a040119a491","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/728b2d17-5a83-41c7-987d-9a040119a491","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/728b2d17-5a83-41c7-987d-9a040119a491","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Airaksinen, M, Bollepalli, B, Juvela, L, Wu, Z, King, S & Alku, P 2016, 'GlottDNN - A full-band glottal vocoder for statistical parametric speech synthesis', Paper presented at Interspeech 2016, San Francisco, United States, 8/09/16 - 12/09/16.","raw_type":"conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W197380572","https://openalex.org/W1499332833","https://openalex.org/W1572730534","https://openalex.org/W1576227399","https://openalex.org/W1963637322","https://openalex.org/W1967884132","https://openalex.org/W1970278793","https://openalex.org/W2021320575","https://openalex.org/W2043003570","https://openalex.org/W2043527182","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2076841080","https://openalex.org/W2097634052","https://openalex.org/W2115039802","https://openalex.org/W2129142580","https://openalex.org/W2153639720","https://openalex.org/W2295121007","https://openalex.org/W2339526801","https://openalex.org/W2395578248","https://openalex.org/W2398742733","https://openalex.org/W2405614646"],"related_works":["https://openalex.org/W153239700","https://openalex.org/W2067459736","https://openalex.org/W2020989338","https://openalex.org/W2105635394","https://openalex.org/W1823617068","https://openalex.org/W2147126679","https://openalex.org/W4300049944","https://openalex.org/W2115039802","https://openalex.org/W2400533375","https://openalex.org/W2470236000"],"abstract_inverted_index":{"GlottHMM":[0,130],"is":[1,44,49],"a":[2,38,71,81,96,113],"previously":[3],"developed":[4],"vocoder":[5,48,61,107],"that":[6,145],"has":[7],"been":[8],"successfully":[9],"used":[10],"in":[11],"HMM-based":[12],"synthesis":[13,119],"by":[14],"parameterizing":[15],"speech":[16],"into":[17],"two":[18],"parts":[19],"(glottal":[20],"flow,":[21],"vocal":[22],"tract)":[23],"according":[24],"to":[25],"the":[26,29,52,59,124,128,133,140,148,152],"functioning":[27],"of":[28,54,70,84,99,102,112,127,139],"real":[30],"human":[31],"voice":[32],"production":[33],"mechanism.":[34],"In":[35],"this":[36],"study,":[37],"new":[39,60,82,97],"glottal":[40,75,90],"vocoding":[41],"method,":[42,78],"GlottDNN,":[43],"proposed.":[45],"The":[46,137],"GlottDNN":[47,66,106,146],"built":[50],"on":[51],"principles":[53],"its":[55],"predecessor,":[56],"GlottHMM,":[57],"but":[58],"introduces":[62],"three":[63],"main":[64],"improvements:":[65],"(1)":[67],"takes":[68],"advantage":[69],"new,":[72],"more":[73],"accurate":[74],"inverse":[76],"filtering":[77],"(2)":[79],"uses":[80],"method":[83],"deep":[85],"neural":[86],"network":[87],"(DNN)":[88],"-based":[89],"excitation":[91],"generation,":[92],"and":[93,121,132],"(3)":[94],"proposes":[95],"approach":[98],"band-wise":[100],"processing":[101],"full-band":[103,114],"speech.<br/>The":[104],"proposed":[105],"was":[108],"evaluated":[109],"as":[110],"part":[111],"state-of-the-art":[115],"DNN-based":[116],"text-to-speech":[117],"(TTS)":[118],"system,":[120],"compared":[122,153],"against":[123],"release":[125],"version":[126],"original":[129],"vocoder,":[131],"well-known":[134],"STRAIGHT":[135],"vocoder.":[136],"results":[138],"subjective":[141],"listening":[142],"test":[143],"indicate":[144],"improves":[147],"TTS":[149],"quality":[150],"over":[151],"methods.":[154]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
