{"id":"https://openalex.org/W2111037747","doi":"https://doi.org/10.1109/icassp.2011.5946438","title":"Vocalistener2: A singing synthesis system able to mimic a user's singing in terms of voice timbre changes as well as pitch and dynamics","display_name":"Vocalistener2: A singing synthesis system able to mimic a user's singing in terms of voice timbre changes as well as pitch and dynamics","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2111037747","doi":"https://doi.org/10.1109/icassp.2011.5946438","mag":"2111037747"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology, Japan","National Institute of Advanced Industrial Science and Technology (AIST), , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), , Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology, Japan","National Institute of Advanced Industrial Science and Technology (AIST), , Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), , Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"456"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9541041851043701},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9263003468513489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251174211502075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.622475266456604},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.5658913254737854},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.5056931972503662},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.47859594225883484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39341142773628235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19376146793365479},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07052344083786011}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9541041851043701},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9263003468513489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251174211502075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.622475266456604},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.5658913254737854},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.5056931972503662},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.47859594225883484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39341142773628235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19376146793365479},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07052344083786011},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2011.5946438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.702.6923","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.702.6923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://staff.aist.go.jp/m.goto/PAPER/ICASSP2011nakano.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.2908","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.2908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://staff.aist.go.jp/t.nakano/PAPER/ICASSP201105nakano.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W11080984","https://openalex.org/W51255321","https://openalex.org/W147487006","https://openalex.org/W1607142029","https://openalex.org/W2042600255","https://openalex.org/W2049686551","https://openalex.org/W2095684756","https://openalex.org/W2097873655","https://openalex.org/W2120605154","https://openalex.org/W2124097505","https://openalex.org/W2125844878","https://openalex.org/W2148846882","https://openalex.org/W2168790345","https://openalex.org/W2170167721","https://openalex.org/W6600459999","https://openalex.org/W6606138395","https://openalex.org/W6636203886","https://openalex.org/W6674766369","https://openalex.org/W6678318511"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W4288088492","https://openalex.org/W1583791393","https://openalex.org/W2982290989","https://openalex.org/W4394924759","https://openalex.org/W2119168266","https://openalex.org/W2886940211"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,12,21,72,124],"singing":[4,13,23,81,106],"synthesis":[5],"system,":[6],"VocaListener2,":[7,69],"that":[8,83],"can":[9,100],"automatically":[10],"synthesize":[11],"voice":[14,47,52,55,73],"by":[15,91,112],"mimicking":[16],"the":[17,62,77,97,104,113,117],"timbre":[18,48,63,74,98],"changes":[19,64,99],"of":[20,30,79],"user's":[22],"voice.":[24,107],"The":[25,108],"system":[26,34,109],"is":[27],"an":[28,120],"extension":[29],"our":[31],"previous":[32,43],"VocaListener":[33],"which":[35],"deals":[36],"with":[37,61],"only":[38],"pitch":[39],"and":[40,54,57,89,123],"dynamics.":[41],"Most":[42],"techniques":[44],"for":[45],"manipulating":[46],"have":[49],"focused":[50],"on":[51,76],"conversion":[53],"morphing,":[56],"they":[58],"cannot":[59],"deal":[60],"during":[65],"singing.":[66],"To":[67],"develop":[68],"we":[70],"constructed":[71],"space":[75,118],"basis":[78],"various":[80],"voices":[82],"are":[84],"synchronized":[85],"under":[86,126],"pitch,":[87],"dynamics,":[88],"phoneme":[90],"using":[92],"VocaListener.":[93],"In":[94],"this":[95],"space,":[96],"be":[101],"reflected":[102],"in":[103,116],"synthesized":[105],"was":[110],"evaluated":[111],"Euclidean":[114],"distance":[115],"between":[119],"estimated":[121],"result":[122],"ground-truth":[125],"closed/open":[127],"conditions.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
