{"id":"https://openalex.org/W2888784223","doi":"https://doi.org/10.21437/interspeech.2018-1239","title":"Naturalness Improvement Algorithm for Reconstructed Glossectomy Patient's Speech Using Spectral Differential Modification in Voice Conversion","display_name":"Naturalness Improvement Algorithm for Reconstructed Glossectomy Patient's Speech Using Spectral Differential Modification in Voice Conversion","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888784223","doi":"https://doi.org/10.21437/interspeech.2018-1239","mag":"2888784223"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1239","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ousar.lib.okayama-u.ac.jp/56199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017529117","display_name":"Hiroki Murakami","orcid":"https://orcid.org/0000-0003-3739-3701"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hiroki Murakami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070197974","display_name":"Sunao Hara","orcid":"https://orcid.org/0000-0001-5972-5178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunao Hara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063057571","display_name":"Masanobu Abe","orcid":"https://orcid.org/0000-0001-9472-5077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masanobu Abe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103159995","display_name":"Masa-aki Sato","orcid":"https://orcid.org/0000-0003-4366-7289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaaki Sato","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109287819","display_name":"Shogo Minagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shogo Minagi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017529117"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5077,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74079779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2464","last_page":"2468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9595000147819519,"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":0.9595000147819519,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.921999990940094,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9089999794960022,"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":0.9303068518638611},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7954989671707153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596741914749146},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6904627084732056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6801744699478149},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6608293056488037},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48412594199180603},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42502760887145996},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.42416971921920776}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9303068518638611},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7954989671707153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596741914749146},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6904627084732056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6801744699478149},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6608293056488037},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48412594199180603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42502760887145996},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.42416971921920776},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1239","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01081:0002948597","is_oa":true,"landing_page_url":"https://ousar.lib.okayama-u.ac.jp/56199","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of Interspeech 2018","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01081:0002948597","is_oa":true,"landing_page_url":"https://ousar.lib.okayama-u.ac.jp/56199","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of Interspeech 2018","raw_type":"conference paper"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2081919107"],"abstract_inverted_index":{"In":[0,123],"this":[1],"paper,":[2],"we":[3,59,110,128],"propose":[4,60],"an":[5],"algorithm":[6,91,140],"to":[7,23,43,61,113,166,169],"improve":[8,44],"the":[9,12,25,48,56,64,115,119,147,154],"naturalness":[10],"of":[11,27,118,125,153,160,171],"reconstructed":[13,165],"glossectomy":[14,75],"patient's":[15],"speech":[16,28,65,98,145],"that":[17,74,138,170],"is":[18,50,73,164],"generated":[19],"by":[20,30],"voice":[21],"conversion":[22],"enhance":[24],"intelligibility":[26,45],"uttered":[29],"patients":[31,76],"with":[32,130],"a":[33,68],"wide":[34],"glossectomy.":[35],"While":[36],"existing":[37],"VC":[38],"algorithms":[39],"make":[40,114],"it":[41],"possible":[42],"and":[46,109,133,162],"naturalness,":[47],"result":[49],"still":[51],"not":[52,84],"satisfying.":[53],"To":[54],"solve":[55],"continuing":[57],"problems,":[58],"directly":[62],"modify":[63],"waveforms":[66],"using":[67],"spectrum":[69,126],"differential.":[70],"The":[71,89],"motivation":[72],"mainly":[77],"have":[78],"problems":[79],"in":[80,85,105,157],"their":[81,86],"vocal":[82,87],"tract,":[83],"cords.":[88],"proposed":[90],"requires":[92],"no":[93,103],"source":[94,106,121],"parameter":[95,107],"extractions":[96,108],"for":[97],"synthesis,":[99],"so":[100],"there":[101],"are":[102,111],"errors":[104],"able":[112],"best":[116],"use":[117],"original":[120],"characteristics.":[122],"terms":[124],"conversion,":[127],"evaluate":[129],"both":[131],"GMM":[132],"DNN.":[134],"Subjective":[135],"evaluations":[136],"show":[137],"our":[139],"can":[141],"synthesize":[142],"more":[143],"natural":[144,172],"than":[146],"vocoder-based":[148],"method.":[149],"Judging":[150],"from":[151],"observations":[152],"spectrogram,":[155],"power":[156],"high-frequency":[158],"bands":[159],"fricatives":[161],"stops":[163],"be":[167],"similar":[168],"speech.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
