{"id":"https://openalex.org/W2146699317","doi":"https://doi.org/10.1109/icassp.2012.6289140","title":"VocaListener and VocaWatcher: Imitating a human singer by using signal processing","display_name":"VocaListener and VocaWatcher: Imitating a human singer by using signal processing","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2146699317","doi":"https://doi.org/10.1109/icassp.2012.6289140","mag":"2146699317"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289140","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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"]}]},{"author_position":"middle","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":"middle","author":{"id":"https://openalex.org/A5102768470","display_name":"Shuuji Kajita","orcid":"https://orcid.org/0000-0001-8188-2209"},"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":"Shuuji Kajita","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":"middle","author":{"id":"https://openalex.org/A5000528849","display_name":"Yosuke Matsusaka","orcid":"https://orcid.org/0000-0002-3508-8423"},"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":"Yosuke Matsusaka","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":"middle","author":{"id":"https://openalex.org/A5012117970","display_name":"Shin\u2019ichiro Nakaoka","orcid":"https://orcid.org/0000-0002-2346-1251"},"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":"Shin'ichiro Nakaoka","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/A5057476470","display_name":"Kazuhito Yokoi","orcid":"https://orcid.org/0000-0003-3942-2027"},"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":"Kazuhito Yokoi","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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5393","last_page":"5396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/singing","display_name":"Singing","score":0.8545303344726562},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8498678207397461},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7983477115631104},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7164658308029175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656731367111206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5899759531021118},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.4773176610469818},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.45100724697113037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.426118940114975},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4119383692741394},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3581673502922058},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22931000590324402},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11767202615737915},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09487569332122803}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8545303344726562},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8498678207397461},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7983477115631104},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7164658308029175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656731367111206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5899759531021118},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.4773176610469818},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.45100724697113037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.426118940114975},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4119383692741394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3581673502922058},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22931000590324402},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11767202615737915},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09487569332122803},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6289140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289140","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:10.1.1.685.9510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.9510","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/ICASSP2012goto.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":30,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W51255321","https://openalex.org/W147487006","https://openalex.org/W1590808459","https://openalex.org/W2004287364","https://openalex.org/W2042600255","https://openalex.org/W2065932863","https://openalex.org/W2087540268","https://openalex.org/W2097873655","https://openalex.org/W2102870814","https://openalex.org/W2111037747","https://openalex.org/W2120605154","https://openalex.org/W2124097505","https://openalex.org/W2129651248","https://openalex.org/W2131471382","https://openalex.org/W2140009279","https://openalex.org/W2148846882","https://openalex.org/W2149411511","https://openalex.org/W2150933458","https://openalex.org/W2161946267","https://openalex.org/W2168790345","https://openalex.org/W2168987487","https://openalex.org/W2170217103","https://openalex.org/W2404424430","https://openalex.org/W6601203246","https://openalex.org/W6606138395","https://openalex.org/W6674766369","https://openalex.org/W6678318511","https://openalex.org/W6679668602","https://openalex.org/W6712942967"],"related_works":["https://openalex.org/W2108382268","https://openalex.org/W2107990538","https://openalex.org/W2089204011","https://openalex.org/W167396688","https://openalex.org/W2407667681","https://openalex.org/W2921576841","https://openalex.org/W1901324946","https://openalex.org/W2395416690","https://openalex.org/W2146699317","https://openalex.org/W2788372077"],"abstract_inverted_index":{"In":[0,57],"this":[1],"paper,":[2],"we":[3],"describe":[4],"three":[5],"singing":[6,16,31,62,85],"information":[7],"processing":[8],"systems,":[9],"VocaListener,":[10],"VocaListener2,":[11],"and":[12,21,35,39,55,78],"VocaWatcher,":[13],"that":[14,86,96],"imitate":[15],"expressions":[17],"of":[18,23,41,70,82],"the":[19,37,42,53,60,74],"voice":[20],"face":[22],"a":[24,71,83,90],"human":[25,43,84],"singer.":[26],"VocaListener":[27],"can":[28,65],"synthesize":[29],"natural":[30],"voices":[32],"by":[33,76,89],"analyzing":[34,77],"imitating":[36,79],"pitch":[38,54],"dynamics":[40],"singing.":[44],"VocaListener2":[45],"imitates":[46],"temporal":[47],"timbre":[48],"changes":[49],"in":[50],"addition":[51],"to":[52],"dynamics.":[56],"synchronization":[58],"with":[59],"synthesized":[61],"voices,":[63],"VocaWatcher":[64],"generate":[66],"realistic":[67],"facial":[68,80],"motions":[69,81],"humanoid":[72],"robot,":[73],"HRP-4C,":[75],"are":[87,100],"recorded":[88],"single":[91],"video":[92],"camera.":[93],"These":[94],"systems":[95],"focus":[97],"on":[98],"\u201cimitation\u201d":[99],"not":[101],"only":[102],"promising":[103],"for":[104,111],"representing":[105],"human-like":[106],"naturalness,":[107],"but":[108],"also":[109],"useful":[110],"providing":[112],"intuitive":[113],"control":[114],"means.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
