{"id":"https://openalex.org/W2399238136","doi":"https://doi.org/10.21437/interspeech.2015-214","title":"Automatic transformation of irregular to regular voice by residual analysis and synthesis","display_name":"Automatic transformation of irregular to regular voice by residual analysis and synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2399238136","doi":"https://doi.org/10.21437/interspeech.2015-214","mag":"2399238136"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-214","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","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/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e9za N\u00e9meth","raw_affiliation_strings":["Budapest University of Technology and Economics"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016031960"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.8629,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83881211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7787058353424072},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7489606142044067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7332935333251953},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6902769804000854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6157819032669067},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.5715489387512207},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5344414114952087},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5088701248168945},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5037924647331238},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4625048041343689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2617936134338379},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21512043476104736}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7787058353424072},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7489606142044067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7332935333251953},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6902769804000854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6157819032669067},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.5715489387512207},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5344414114952087},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5088701248168945},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5037924647331238},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4625048041343689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2617936134338379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21512043476104736},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-214","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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":24,"referenced_works":["https://openalex.org/W78415016","https://openalex.org/W101581914","https://openalex.org/W134844091","https://openalex.org/W1534696585","https://openalex.org/W1574850502","https://openalex.org/W1980988001","https://openalex.org/W2010070470","https://openalex.org/W2022194925","https://openalex.org/W2045764233","https://openalex.org/W2075813705","https://openalex.org/W2096760972","https://openalex.org/W2108475147","https://openalex.org/W2109138290","https://openalex.org/W2109189270","https://openalex.org/W2110392754","https://openalex.org/W2121258852","https://openalex.org/W2122334831","https://openalex.org/W2136101712","https://openalex.org/W2145892079","https://openalex.org/W2149395423","https://openalex.org/W2151890809","https://openalex.org/W2160221523","https://openalex.org/W2404911693","https://openalex.org/W2542179260"],"related_works":["https://openalex.org/W2014919663","https://openalex.org/W2171564668","https://openalex.org/W2110375858","https://openalex.org/W2365863649","https://openalex.org/W2367622526","https://openalex.org/W2372081722","https://openalex.org/W2377001183","https://openalex.org/W2136885550","https://openalex.org/W2369158369","https://openalex.org/W2381098171"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"automatic":[4],"speech":[5,12,52,65,79,90],"transformation":[6,19],"method":[7],"of":[8,11,41,48,51,61,87],"non-ideal":[9],"phonation":[10],"(irregular":[13],"or":[14],"creaky":[15],"voice).":[16],"The":[17,44],"irregular-to-regular":[18],"is":[20,34,53,66,91],"performed":[21],"by":[22,55,76],"analyzing":[23],"and":[24],"resynthesizing":[25],"the":[26,69,84,88],"residual.":[27,70],"A":[28,71],"recent":[29],"continuous":[30],"pitch":[31],"estimation":[32],"algorithm":[33],"used":[35],"for":[36],"interpolating":[37],"F0":[38],"in":[39],"regions":[40],"irregular":[42,49,82],"voice.":[43],"linear":[45],"prediction":[46],"residual":[47],"sections":[50],"replaced":[54],"overlap-added":[56],"frames":[57],"from":[58,68],"a":[59],"codebook":[60],"pitch-synchronous":[62],"residuals.":[63],"Finally,":[64],"reconstructed":[67],"listening":[72],"experiment":[73],"showed":[74],"that":[75],"transforming":[77],"natural":[78],"samples":[80],"containing":[81],"voice,":[83],"perceived":[85],"roughness":[86],"transformed":[89],"decreased.":[92]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
