{"id":"https://openalex.org/W2404839462","doi":"https://doi.org/10.1109/icassp.2016.7472664","title":"Exemplar-based sparse representation of timbre and prosody for voice conversion","display_name":"Exemplar-based sparse representation of timbre and prosody for voice conversion","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2404839462","doi":"https://doi.org/10.1109/icassp.2016.7472664","mag":"2404839462"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110320609","display_name":"Huaiping Ming","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Huaiping Ming","raw_affiliation_strings":["Institute for Infocomm Research A*STAR, Singapore","School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Institute for Infocomm Research A*STAR, Singapore; School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Institute for Infocomm Research A*STAR, Singapore; School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I17145004","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112133862","display_name":"Dongyan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["Institute for Infocomm Research A*STAR, Singapore","Institute for Infocomm Research, A(\u204e)STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A(\u204e)STAR, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China","School of Computer Science, Northwestern Polytechnical University, Xi'An, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'An, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084317268","display_name":"Shaofei Zhang","orcid":"https://orcid.org/0000-0002-8377-2270"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China","School of Computer Science, Northwestern Polytechnical University, Xi'An, China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'An, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Institute for Infocomm Research A*STAR, Singapore","Institute for Infocomm Research, A(\u204e)STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A(\u204e)STAR, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research A*STAR, Singapore","Institute for Infocomm Research, A(\u204e)STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A(\u204e)STAR, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110320609"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I17145004","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":8.141,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.97495938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"5175","last_page":"5179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.9202374815940857},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8460973501205444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7243872880935669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.709018349647522},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5873676538467407},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5762059688568115},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5250130295753479},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24364018440246582},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.06561627984046936}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9202374815940857},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8460973501205444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7243872880935669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709018349647522},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5873676538467407},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5762059688568115},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5250130295753479},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24364018440246582},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.06561627984046936},{"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/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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W188951208","https://openalex.org/W1505264225","https://openalex.org/W1540083112","https://openalex.org/W1676678427","https://openalex.org/W1965912016","https://openalex.org/W1977362459","https://openalex.org/W2005438552","https://openalex.org/W2085393504","https://openalex.org/W2086796102","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2127589467","https://openalex.org/W2131062138","https://openalex.org/W2151262064","https://openalex.org/W2153425803","https://openalex.org/W2154278880","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2165674530","https://openalex.org/W2182290009","https://openalex.org/W2185573909","https://openalex.org/W2294246205","https://openalex.org/W2296704011","https://openalex.org/W2395980997","https://openalex.org/W2406654659","https://openalex.org/W2408732577","https://openalex.org/W2577042574","https://openalex.org/W6603838645","https://openalex.org/W6630263700","https://openalex.org/W6637350648","https://openalex.org/W6686074763","https://openalex.org/W6697270646","https://openalex.org/W6712034360","https://openalex.org/W6732251480"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2054460271"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,27,67,74,87,93],"(VC)":[2],"aims":[3],"to":[4,9,85],"make":[5],"one":[6],"speaker":[7,15,36,102],"(source)":[8],"sound":[10],"like":[11],"spoken":[12],"by":[13,40],"another":[14],"(target)":[16],"without":[17],"changing":[18],"the":[19,24,35,41,86,91,99,105],"language":[20],"content.":[21],"Most":[22],"of":[23,61,88,94,104],"state-of-the-art":[25],"voice":[26,66],"systems":[28],"focus":[29],"only":[30],"on":[31],"timbre":[32,62,73],"conversion.":[33],"However,":[34],"identity":[37,103],"is":[38],"characterized":[39],"source-related":[42],"cues":[43],"such":[44],"as":[45,50],"fundamental":[46],"frequency":[47],"and":[48,63,75,101],"energy":[49],"well.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"propose":[56],"an":[57],"exemplarbased":[58],"sparse":[59],"representation":[60],"prosody":[64,76,95],"for":[65],"that":[68],"does":[69],"not":[70],"necessitate":[71],"separately":[72],"conversions.":[77],"The":[78],"experiment":[79],"results":[80],"show":[81],"that,":[82],"in":[83],"addition":[84],"spectral":[89],"features,":[90],"proper":[92],"features":[96],"will":[97],"improve":[98],"quality":[100],"converted":[106],"speech.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}