{"id":"https://openalex.org/W2786220077","doi":"https://doi.org/10.1109/apsipa.2017.8282283","title":"An investigation of how to design control parameters for statistical voice timbre control","display_name":"An investigation of how to design control parameters for statistical voice timbre control","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786220077","doi":"https://doi.org/10.1109/apsipa.2017.8282283","mag":"2786220077"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5040831871","display_name":"Kubo Kazutaka","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":"Kazutaka Kubo","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","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":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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/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":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"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":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"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 and Technology (NAIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1520","last_page":"1523"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/timbre","display_name":"Timbre","score":0.9708248972892761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6803368926048279},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6765556335449219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6704729795455933},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5532684326171875},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.49692800641059875},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49507513642311096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2804485559463501},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21299630403518677}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9708248972892761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6803368926048279},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6765556335449219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6704729795455933},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5532684326171875},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.49692800641059875},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49507513642311096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2804485559463501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21299630403518677},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":9,"referenced_works":["https://openalex.org/W1523372075","https://openalex.org/W1581272224","https://openalex.org/W2049686551","https://openalex.org/W2052871313","https://openalex.org/W2077865492","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2395578248","https://openalex.org/W6631309588"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2164760767"],"abstract_inverted_index":{"Multiple-regression":[0],"Gaussian":[1],"mixture":[2],"models":[3],"(MR-GMM)":[4],"allow":[5],"for":[6,163,197],"control":[7,47,58,81,133,142,169,189],"of":[8,85,115,119,153,165,185,204],"voice":[9,18,31,45,63,79,110,123,131,140,167,187,201],"timbre":[10,19,32,46,64,80,132,141,168,188,202],"along":[11],"several":[12],"axes":[13],"each":[14,86,98,154],"described":[15],"by":[16],"a":[17,161],"expression":[20,33,65],"word.":[21],"To":[22],"create":[23],"these":[24],"axes,":[25],"perceptual":[26],"scores":[27],"corresponding":[28,54,147],"to":[29,38,55,97,128],"multiple":[30],"words":[34,66,72],"are":[35,60,67,83,93,151],"manually":[36],"assigned":[37],"individual":[39,57],"pre-stored":[40],"target":[41],"speakers":[42],"as":[43],"the":[44,56,78,89,108,113,116,130,139,146,166,172,183,186,199,205],"parameters,":[48],"and":[49,100,181,191],"then":[50],"acoustic":[51,148,192],"basis":[52,91,149,193],"vectors":[53,92,150,194],"parameters":[59,82,134,143,170,190],"learned.":[61],"The":[62],"usually":[68],"selected":[69],"from":[70],"various":[71],"using":[73,171],"factor":[74],"analysis":[75],"so":[76,135],"that":[77,136,159],"independent":[84,152],"other.":[87,155],"However,":[88],"resulting":[90],"not":[94,137],"often":[95],"orthogonal":[96],"other,":[99],"they":[101],"practically":[102],"cause":[103],"difficulties":[104],"in":[105],"intuitively":[106,120],"controlling":[107,121],"converted":[109,122,173,200],"timbre.":[111],"Towards":[112],"development":[114],"MR-GMM":[117],"capable":[118],"timbre,":[124],"we":[125],"investigate":[126],"how":[127],"design":[129],"only":[138],"but":[144],"also":[145],"Experimental":[156],"results":[157],"demonstrate":[158],"1)":[160],"method":[162],"annotation":[164],"voices":[174,178],"rather":[175],"than":[176],"natural":[177],"is":[179,195],"effective,":[180],"2)":[182],"independences":[184],"helpful":[196],"improving":[198],"controllability":[203],"MR-GMM.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
