{"id":"https://openalex.org/W2139627492","doi":"https://doi.org/10.1109/icassp.2012.6287949","title":"Statistical approach to voice quality control in esophageal speech enhancement","display_name":"Statistical approach to voice quality control in esophageal speech enhancement","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2139627492","doi":"https://doi.org/10.1109/icassp.2012.6287949","mag":"2139627492"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113974812","display_name":"Kenzo Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenzo Yamamoto","raw_affiliation_strings":["Graduate school of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate school of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Graduate school of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate school of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024608998","display_name":"Hironori Doi","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hironori Doi","raw_affiliation_strings":["Graduate school of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate school of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate school of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate school of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyohiro Shikano","raw_affiliation_strings":["Graduate school of Information Science, Nara Institute of Science and Technology, Japan","Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate school of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"57","issue":null,"first_page":"4497","last_page":"4500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10863","display_name":"Voice and Speech Disorders","score":0.98580002784729,"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/esophageal-speech","display_name":"Esophageal speech","score":0.8256223797798157},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7792032957077026},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7720773220062256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7442276477813721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6986333131790161},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6143781542778015},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.610300600528717},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5479904413223267},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5135602951049805},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.50295490026474},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47158515453338623},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4665733575820923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2627086639404297}],"concepts":[{"id":"https://openalex.org/C107400117","wikidata":"https://www.wikidata.org/wiki/Q3562529","display_name":"Esophageal speech","level":4,"score":0.8256223797798157},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7792032957077026},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7720773220062256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442276477813721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6986333131790161},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6143781542778015},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.610300600528717},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5479904413223267},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5135602951049805},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.50295490026474},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47158515453338623},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4665733575820923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2627086639404297},{"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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2780474809","wikidata":"https://www.wikidata.org/wiki/Q9637","display_name":"Larynx","level":2,"score":0.0},{"id":"https://openalex.org/C2781157581","wikidata":"https://www.wikidata.org/wiki/Q1472065","display_name":"Laryngectomy","level":3,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6287949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.222.7891","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.7891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://spalab.naist.jp/%7Etomoki/Tomoki/Conferences/ICASSP2012_ES2SP-VQC.pdf","raw_type":"text"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783337","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4886","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783337","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4886","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8007057964","display_name":"Development of technologies for next-generation voice changer towards barrier-free speech communication","funder_award_id":"22680016","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W95922436","https://openalex.org/W1966504338","https://openalex.org/W2007023536","https://openalex.org/W2039800941","https://openalex.org/W2049686551","https://openalex.org/W2078722660","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2165108269","https://openalex.org/W6603918624"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W173498260","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2851491717","https://openalex.org/W4252682934","https://openalex.org/W2072884270","https://openalex.org/W2990418459"],"abstract_inverted_index":{"This":[0,70],"paper":[1],"describes":[2],"a":[3,55,80,107],"voice":[4,40,57,77,83,103,116],"quality":[5,41,78,104],"control":[6,100],"method":[7,59,71,125],"in":[8],"statistical":[9,56],"esophageal":[10,61],"speech":[11,14,62,65],"enhancement.":[12],"Esophageal":[13],"is":[15,72,118,126],"produced":[16],"by":[17,47,54,105,128],"one":[18],"of":[19,35,74,122],"the":[20,101,123],"alternative":[21],"speaking":[22],"methods":[23],"for":[24],"laryngectomees.":[25,49],"Its":[26],"naturalness":[27],"and":[28,38],"intelligibility":[29],"are":[30,52],"much":[31],"lower":[32],"than":[33],"those":[34],"natural":[36],"voices":[37],"its":[39],"sounds":[42],"similar":[43],"even":[44,112],"if":[45,113],"uttered":[46],"different":[48],"These":[50],"issues":[51],"alleviated":[53],"conversion":[58],"from":[60],"into":[63],"normal":[64],"(ES-to-Speech)":[66],"based":[67],"on":[68],"eigenvoices.":[69],"capable":[73],"determining":[75],"converted":[76,102],"using":[79,91],"few":[81,108],"target":[82,115],"samples.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"propose":[89],"ES-to-Speech":[90],"regression":[92],"techniques":[93],"to":[94,98],"make":[95],"it":[96],"possible":[97],"manually":[99],"manipulating":[106],"intuitively":[109],"controllable":[110],"parameters":[111],"no":[114],"sample":[117],"available.":[119],"The":[120],"effectiveness":[121],"proposed":[124],"confirmed":[127],"experimental":[129],"evaluations.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
