{"id":"https://openalex.org/W3114898335","doi":"https://doi.org/10.23919/eusipco47968.2020.9287721","title":"Implementation of low-latency electrolaryngeal speech enhancement based on multi-task CLDNN","display_name":"Implementation of low-latency electrolaryngeal speech enhancement based on multi-task CLDNN","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3114898335","doi":"https://doi.org/10.23919/eusipco47968.2020.9287721","mag":"3114898335"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287721","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th 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, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, 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, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, 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":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"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":0.9993000030517578,"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/T13289","display_name":"Infant Health and Development","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8105385303497314},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.729990541934967},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7227068543434143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7173451781272888},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6194512844085693},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5186811685562134},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5177554488182068},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49852538108825684},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4614516496658325},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4560149013996124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3479364216327667},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1929716169834137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105385303497314},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.729990541934967},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7227068543434143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7173451781272888},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6194512844085693},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5186811685562134},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5177554488182068},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49852538108825684},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4614516496658325},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4560149013996124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3479364216327667},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1929716169834137},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287721","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W240387242","https://openalex.org/W1491561031","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1821462560","https://openalex.org/W1968939597","https://openalex.org/W2013996527","https://openalex.org/W2022125261","https://openalex.org/W2023694213","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/W2159202424","https://openalex.org/W2518172956","https://openalex.org/W2746474733","https://openalex.org/W2803023299","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2901291025","https://openalex.org/W2902967674","https://openalex.org/W2913178639","https://openalex.org/W2936774411","https://openalex.org/W2943553228","https://openalex.org/W2963035245","https://openalex.org/W2963971656","https://openalex.org/W2964222566","https://openalex.org/W2973216307","https://openalex.org/W2991015288","https://openalex.org/W2994715919","https://openalex.org/W2996414377","https://openalex.org/W3096567388","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W6609372888","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6682209637","https://openalex.org/W6683207941","https://openalex.org/W6751751081","https://openalex.org/W6771070734"],"related_works":["https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W2079655441","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W2023694213","https://openalex.org/W2958354987","https://openalex.org/W2146137281","https://openalex.org/W2182429542"],"abstract_inverted_index":{"In":[0,64],"this":[1,43,65,123,126],"paper,":[2,127],"we":[3,128,151],"propose":[4,129,153],"a":[5,110],"low-latency":[6,138],"speech":[7,13,21,33,47,74,102,140,191],"enhancement":[8,48],"technique":[9,49],"for":[10,93,115,136],"electrolaryngeal":[11],"(EL)":[12],"based":[14,50,88],"on":[15,51,89],"multi-task":[16,130],"CLDNN.":[17],"Although":[18],"the":[19,37,72,116,119,137,148,154,172,184,194],"EL":[20,46,73,139],"can":[22],"generate":[23],"relatively":[24],"intelligible":[25],"speech,":[26],"laryngectomees":[27],"always":[28],"suffer":[29],"quality":[30],"degradation":[31],"of":[32,54,71,118],"naturalness":[34,189],"due":[35],"to":[36,100,113,143,147,178,183],"mechanical":[38],"excitation":[39,83],"signals.":[40],"To":[41,121],"solve":[42],"problem,":[44],"an":[45,67],"CLDNN":[52,131,186],"consisting":[53],"convolution,":[55],"recurrent,":[56],"and":[57,85,163,187,190],"fully":[58],"connected":[59],"layers":[60,108,135],"has":[61],"been":[62],"proposed.":[63],"technique,":[66],"input":[68],"feature":[69],"vector":[70],"is":[75,98],"converted":[76],"into":[77],"several":[78],"vocoder":[79],"parameters":[80,84,87],"such":[81],"as":[82],"spectral":[86],"expert":[90],"CLDNNs":[91],"optimized":[92],"each":[94],"feature.":[95],"However,":[96],"it":[97,176],"difficult":[99],"utilize":[101],"communication":[103],"because":[104],"its":[105],"bi-directional":[106,149,185],"recurrent":[107,134],"cause":[109],"large":[111],"delay":[112],"wait":[114],"end":[117],"utterance.":[120],"address":[122],"issue,":[124],"in":[125,193],"with":[132],"uni-directional":[133],"enhancement.":[141],"Moreover,":[142],"achieve":[144,179],"comparable":[145,180],"performance":[146],"CLDNN,":[150],"also":[152],"following":[155],"techniques:":[156],"1)":[157],"knowledge":[158],"distillation,":[159],"2)":[160],"data":[161],"augmentation,":[162],"3)":[164],"phonetic":[165],"regularization.":[166],"The":[167],"experimental":[168],"results":[169,182],"demonstrate":[170],"that":[171],"proposed":[173],"method":[174],"makes":[175],"possible":[177],"objective":[181],"outperform":[188],"intelligibility":[192],"noisy":[195],"condition.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}