{"id":"https://openalex.org/W2902967674","doi":"https://doi.org/10.23919/eusipco.2018.8553154","title":"Electrolaryngeal Speech Enhancement with Statistical Voice Conversion based on CLDNN","display_name":"Electrolaryngeal Speech Enhancement with Statistical Voice Conversion based on CLDNN","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902967674","doi":"https://doi.org/10.23919/eusipco.2018.8553154","mag":"2902967674"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553154","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2115","last_page":"2119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7831867933273315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7690293788909912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481647729873657},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6317824721336365},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.537138819694519},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4948350787162781},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49170953035354614},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4526781737804413},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42250558733940125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059573709964752},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33176302909851074},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1009330153465271},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0733039379119873}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7831867933273315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7690293788909912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481647729873657},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6317824721336365},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.537138819694519},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4948350787162781},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49170953035354614},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4526781737804413},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42250558733940125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059573709964752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33176302909851074},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1009330153465271},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0733039379119873},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2018.8553154","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W240387242","https://openalex.org/W1509691205","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W1968939597","https://openalex.org/W2013996527","https://openalex.org/W2022125261","https://openalex.org/W2023694213","https://openalex.org/W2049686551","https://openalex.org/W2086796102","https://openalex.org/W2096779346","https://openalex.org/W2116593694","https://openalex.org/W2120605154","https://openalex.org/W2128653836","https://openalex.org/W2145892079","https://openalex.org/W2151500768","https://openalex.org/W2294351487","https://openalex.org/W2395578248","https://openalex.org/W2473388484","https://openalex.org/W2532494225","https://openalex.org/W2611961223","https://openalex.org/W2746474733","https://openalex.org/W2749651610","https://openalex.org/W2963971656","https://openalex.org/W6609372888","https://openalex.org/W6631943919","https://openalex.org/W6672305501","https://openalex.org/W6682209637"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2024201202","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751"],"abstract_inverted_index":{"An":[0],"electrolarynx":[1],"(EL)":[2],"is":[3,32,74,116],"a":[4,49],"widely":[5],"used":[6],"device":[7],"to":[8,18,40,64,104,166,178,186],"mechanically":[9],"generate":[10],"excitation":[11,43,91],"signals,":[12],"making":[13],"it":[14,102],"possible":[15,103],"for":[16],"laryngectomees":[17],"produce":[19],"EL":[20,27,65,72,86,110,114,130,168],"speech":[21,28,38,66,73,79,87,95,115,131,169],"without":[22],"vocal":[23],"fold":[24],"vibrations.":[25],"Although":[26,98],"sounds":[29],"relatively":[30],"intelligible,":[31],"significantly":[33,105,201],"less":[34],"natural":[35],"than":[36],"normal":[37,78,94,122],"owing":[39],"its":[41],"mechanical":[42],"signals.":[44],"To":[45,124],"address":[46],"this":[47,69,99,134],"issue,":[48],"statistical":[50,129],"voice":[51],"conversion":[52,140],"(VC)":[53],"technique":[54,100],"based":[55,142],"on":[56,143],"Gaussian":[57],"mixture":[58],"models":[59],"(GMMs)":[60],"has":[61],"been":[62],"applied":[63],"enhancement.":[67],"In":[68],"technique,":[70],"input":[71],"converted":[75],"into":[76,88,172,181,189],"target":[77,121],"by":[80],"converting":[81],"spectral":[82,89,170,173],"features":[83,171],"of":[84,93,109,128,146,208],"the":[85,107,112,120,126,198,203],"and":[90,154,174,184,213],"parameters":[92],"using":[96],"GMMs.":[97],"makes":[101],"improve":[106,125],"naturalness":[108],"speech,":[111],"enhanced":[113],"still":[117],"far":[118],"from":[119],"speech.":[123],"performance":[127],"enhancement,":[132],"in":[133,206],"paper,":[135],"we":[136],"propose":[137],"an":[138],"EL-to-speech":[139],"method":[141,200,205],"CLDNNs":[144,162],"consisting":[145],"convolutional":[147],"layers,":[148,153],"long":[149],"short-term":[150],"memory":[151],"recurrent":[152],"fully":[155],"connected":[156],"deep":[157],"neural":[158],"network":[159],"layers.":[160],"Three":[161],"are":[163],"trained,":[164],"one":[165,177,185],"convert":[167,179,187],"band-aperiodicity":[175],"parameters,":[176],"them":[180,188],"unvoiced/voiced":[182],"symbols,":[183],"continuous":[190],"F0":[191],"patterns.":[192],"The":[193],"experimental":[194],"results":[195],"demonstrate":[196],"that":[197],"proposed":[199],"outperforms":[202],"conventional":[204],"terms":[207],"both":[209],"objective":[210],"evaluation":[211,215],"metrics":[212],"subjective":[214],"scores.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}