{"id":"https://openalex.org/W4372266901","doi":"https://doi.org/10.1109/icassp49357.2023.10096442","title":"Low-Latency Electrolaryngeal Speech Enhancement Based on Fastspeech2-Based Voice Conversion and Self-Supervised Speech Representation","display_name":"Low-Latency Electrolaryngeal Speech Enhancement Based on Fastspeech2-Based Voice Conversion and Self-Supervised Speech Representation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266901","doi":"https://doi.org/10.1109/icassp49357.2023.10096442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":["Nagoya University,Japan","Nagoya University, Japan","TARVO, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"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 Hayashi","raw_affiliation_strings":["Nagoya University,Japan","TARVO, Inc., Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9943000078201294,"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":0.7749612331390381},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7671622037887573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7426745891571045},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6109810471534729},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5512307286262512},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5483022332191467},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5233927369117737},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5006065368652344},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47392114996910095},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45056265592575073},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4483097493648529},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.44735443592071533},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4410054683685303},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4176808297634125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3622949719429016},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1260330080986023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749612331390381},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7671622037887573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7426745891571045},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6109810471534729},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5512307286262512},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5483022332191467},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5233927369117737},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5006065368652344},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47392114996910095},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45056265592575073},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4483097493648529},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.44735443592071533},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4410054683685303},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4176808297634125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3622949719429016},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1260330080986023},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W2023694213","https://openalex.org/W2120605154","https://openalex.org/W2800289214","https://openalex.org/W2897353073","https://openalex.org/W2902967674","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2973216307","https://openalex.org/W2979476256","https://openalex.org/W2996414377","https://openalex.org/W3002433751","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3099078140","https://openalex.org/W3100378519","https://openalex.org/W3101689408","https://openalex.org/W3114898335","https://openalex.org/W3156592906","https://openalex.org/W3162517041","https://openalex.org/W3173432002","https://openalex.org/W3193566630","https://openalex.org/W3197763626","https://openalex.org/W3207300132","https://openalex.org/W3209059054","https://openalex.org/W4210590938","https://openalex.org/W4224923642","https://openalex.org/W4226039367","https://openalex.org/W4283024503","https://openalex.org/W4306155393","https://openalex.org/W4307008149","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6769196770","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6795666162","https://openalex.org/W6845683064"],"related_works":["https://openalex.org/W2159307410","https://openalex.org/W4319347033","https://openalex.org/W1542588102","https://openalex.org/W2020464095","https://openalex.org/W2151333624","https://openalex.org/W1890431648","https://openalex.org/W1572861854","https://openalex.org/W1987001738","https://openalex.org/W1968776176","https://openalex.org/W1591426470"],"abstract_inverted_index":{"In":[0],"this":[1,78,81],"paper,":[2,82],"we":[3,83,107],"propose":[4,84,109],"a":[5,85,115],"low-latency":[6,16,86],"sequence-to-sequence":[7,87],"speech":[8,18,35,48,57,69,89,117,159],"enhancement":[9,19,90,160],"technique":[10,20,91],"for":[11],"electrolaryngeal":[12],"(EL)":[13],"speech.":[14,41],"A":[15],"EL":[17,40,88,158],"based":[21,92],"on":[22,93],"CLDNN":[23],"was":[24],"previously":[25],"proposed":[26,142],"to":[27,30,37,59,97,129,154],"enable":[28],"laryngectomees":[29],"produce":[31],"relatively":[32],"naturally":[33],"sounding":[34],"compared":[36,153],"the":[38,43,46,55,110,124,141,155],"original":[39],"However,":[42],"naturalness":[44],"of":[45,54,63],"enhanced":[47],"is":[49],"still":[50],"far":[51],"from":[52],"that":[53,140],"natural":[56],"due":[58],"insufficient":[60],"modeling":[61],"accuracy":[62],"an":[64],"acoustic":[65],"feature":[66],"sequence":[67],"and":[68,105,120,126,150],"waveform":[70],"caused":[71],"by":[72],"frame-wise":[73],"conversion":[74],"processing.":[75],"To":[76],"solve":[77],"problem,":[79],"in":[80,133,147],"CLDNN-FastSpeech2-based":[94],"VC.":[95],"Moreover,":[96],"improve":[98],"various":[99],"factors":[100],"such":[101],"as":[102],"naturalness,":[103],"intelligibility,":[104],"robustness,":[106],"also":[108],"following":[111],"techniques:":[112],"1)":[113],"utilizing":[114],"self-supervised":[116],"representation":[118],"(SSL)":[119],"2)":[121],"randomly":[122],"sampling":[123],"predicted":[125],"ground-truth":[127],"features":[128],"alleviate":[130],"prediction":[131],"errors":[132],"variance":[134],"adaptor.":[135],"The":[136],"experimental":[137],"results":[138],"demonstrate":[139],"method":[143],"yields":[144],"better":[145],"performance":[146],"both":[148],"objective":[149],"subjective":[151],"evaluations":[152],"conventional":[156],"frame-based":[157],"technique.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}