{"id":"https://openalex.org/W2406009389","doi":"https://doi.org/10.21437/interspeech.2015-138","title":"Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential","display_name":"Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2406009389","doi":"https://doi.org/10.21437/interspeech.2015-138","mag":"2406009389"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-138","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-138","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/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science & Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5050897938"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89194131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3350","last_page":"3354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.8230588436126709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014205455780029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6845149397850037},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6015567779541016},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4861464202404022},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4473263621330261},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4212181568145752},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3573206663131714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482000231742859},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07756143808364868}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8230588436126709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014205455780029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6845149397850037},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6015567779541016},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4861464202404022},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4473263621330261},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4212181568145752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3573206663131714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482000231742859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07756143808364868},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-138","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-138","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W208520372","https://openalex.org/W1505583828","https://openalex.org/W1543281296","https://openalex.org/W1589867908","https://openalex.org/W1751815199","https://openalex.org/W1982854652","https://openalex.org/W1987992317","https://openalex.org/W1990394889","https://openalex.org/W2034829178","https://openalex.org/W2049686551","https://openalex.org/W2054764113","https://openalex.org/W2079402412","https://openalex.org/W2120605154","https://openalex.org/W2141684970","https://openalex.org/W2143493821","https://openalex.org/W2293872531","https://openalex.org/W2294038178"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2039489009","https://openalex.org/W1578916557"],"abstract_inverted_index":{"In":[0],"our":[1],"previous":[2],"work,":[3],"we":[4,72],"have":[5],"developed":[6],"a":[7,29,63,91,138],"speech":[8,55,88,134],"modification":[9,124],"system":[10,48],"capable":[11],"of":[12,39,52,77,94,140],"manipulating":[13,146],"unobserved":[14,148],"articulatory":[15,149],"movements":[16],"by":[17,57,145],"sequentially":[18],"performing":[19],"speech-to-articulatory":[20],"inversion":[21],"mapping":[22,26,36],"and":[23,59,101],"articulatory-to-speech":[24],"production":[25],"based":[27],"on":[28],"Gaussian":[30],"mixture":[31],"model":[32],"(GMM)-based":[33],"statistical":[34],"feature":[35],"technique.":[37],"One":[38],"the":[40,53,120,132,147],"biggest":[41],"issues":[42],"to":[43,108],"be":[44],"addressed":[45],"in":[46,62,106,131],"this":[47,70],"is":[49],"quality":[50,129],"degradation":[51],"synthetic":[54,133],"caused":[56],"modeling":[58],"conversion":[60],"errors":[61],"vocoderbased":[64,111],"waveform":[65,79,89,123],"generation":[66],"framework.":[67],"To":[68],"address":[69],"issue,":[71],"propose":[73],"several":[74],"implementation":[75],"methods":[76,83,125],"direct":[78,122],"modification.":[80],"The":[81,115],"proposed":[82,121],"directly":[84],"filter":[85],"an":[86],"input":[87],"with":[90],"time":[92],"sequence":[93],"spectral":[95,103],"differential":[96],"parameters":[97,105],"calculated":[98],"between":[99],"unmodified":[100],"modified":[102],"envelop":[104],"order":[107],"avoid":[109],"using":[110],"excitation":[112],"signal":[113],"generation.":[114],"experimental":[116],"results":[117],"show":[118],"that":[119],"yield":[126],"significantly":[127],"larger":[128],"improvements":[130],"while":[135],"also":[136],"keeping":[137],"capability":[139],"intuitively":[141],"modifying":[142],"phoneme":[143],"sounds":[144],"movements.":[150]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
