{"id":"https://openalex.org/W2398742733","doi":"https://doi.org/10.21437/interspeech.2014-444","title":"Deep neural network based trainable voice source model for synthesis of speech with varying vocal effort","display_name":"Deep neural network based trainable voice source model for synthesis of speech with varying vocal effort","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2398742733","doi":"https://doi.org/10.21437/interspeech.2014-444","mag":"2398742733"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"article","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/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009644866","display_name":"Antti Suni","orcid":"https://orcid.org/0000-0003-3414-6035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antti Suni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040474925","display_name":"Martti Vainio","orcid":"https://orcid.org/0000-0003-2570-0196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martti Vainio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3436,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96624214,"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":"1969","last_page":"1973"},"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":0.9980000257492065,"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":0.9940999746322632,"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":0.7884445190429688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7483310699462891},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5873133540153503},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5664317011833191},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5503390431404114},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5095232129096985},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.47703975439071655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3582456409931183},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08838176727294922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884445190429688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7483310699462891},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5873133540153503},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5664317011833191},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5503390431404114},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5095232129096985},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.47703975439071655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3582456409931183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08838176727294922},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W6725010","https://openalex.org/W68089216","https://openalex.org/W80543058","https://openalex.org/W86509243","https://openalex.org/W163616957","https://openalex.org/W200094172","https://openalex.org/W1600722501","https://openalex.org/W1756939916","https://openalex.org/W1861150963","https://openalex.org/W1966264494","https://openalex.org/W2021320575","https://openalex.org/W2039800941","https://openalex.org/W2049083033","https://openalex.org/W2049686551","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2075510576","https://openalex.org/W2089935964","https://openalex.org/W2097634052","https://openalex.org/W2100213313","https://openalex.org/W2102003408","https://openalex.org/W2103764823","https://openalex.org/W2117418893","https://openalex.org/W2121258852","https://openalex.org/W2129142580","https://openalex.org/W2139913386","https://openalex.org/W2147215240","https://openalex.org/W2149572519","https://openalex.org/W2150658333","https://openalex.org/W2150906086","https://openalex.org/W2153914468","https://openalex.org/W2155498861","https://openalex.org/W2158432602","https://openalex.org/W2184045248","https://openalex.org/W2228674556","https://openalex.org/W2285182995","https://openalex.org/W2286166914","https://openalex.org/W2395578248","https://openalex.org/W2400063444","https://openalex.org/W2406009315"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2039489009","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"a":[3,29,43,63,70,81,102,124,136,167,170],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"based":[8,88,109],"voice":[9,25,46,65,78,96,132],"source":[10,26,47,79,97,133],"modelling":[11,107],"method":[12,108,146],"in":[13],"the":[14,32,36,75,90,131,143,151,156,160],"synthesis":[15],"of":[16,159],"speech":[17,53],"with":[18,51],"varying":[19],"vocal":[20,119],"effort.":[21],"The":[22,45,94],"new":[23],"trainable":[24],"model":[27,48,98],"learns":[28],"mapping":[30],"between":[31],"acoustic":[33,92],"features":[34],"and":[35,58,73,104,122,162],"time-domain":[37],"pitch-synchronous":[38],"glottal":[39,114],"flow":[40,115],"waveform":[41,84],"using":[42,74,123,169],"DNN.":[44],"is":[49,66,85,99,147,163],"trained":[50],"various":[52],"material":[54],"from":[55],"breathy,":[56],"normal,":[57],"Lombard":[59],"speech.":[60],"In":[61],"synthesis,":[62],"normal":[64],"first":[67],"adapted":[68,91],"to":[69,101,128,135,150],"desired":[71,137],"style,":[72],"flexible":[76],"DNN-based":[77,145],"model,":[80],"style-specific":[82],"excitation":[83,106],"automatically":[86],"generated":[87],"on":[89,110],"features.":[93],"proposed":[95,144],"compared":[100],"robust":[103],"high-quality":[105],"manually":[111],"selected":[112],"mean":[113],"pulses":[116,161],"for":[117],"each":[118],"effort":[120],"level":[121],"spectral":[125,171],"matching":[126,172],"filter":[127],"correctly":[129],"match":[130],"spectrum":[134],"style.":[138],"Subjective":[139],"evaluations":[140],"show":[141],"that":[142],"rated":[148],"comparable":[149],"baseline":[152],"method,":[153],"but":[154],"avoids":[155],"manual":[157],"selection":[158],"computationally":[164],"faster":[165],"than":[166],"system":[168],"filter.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}