{"id":"https://openalex.org/W1997035035","doi":"https://doi.org/10.1109/icassp.2013.6639002","title":"A style capturing approach to F0 transformation in voice conversion","display_name":"A style capturing approach to F0 transformation in voice conversion","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1997035035","doi":"https://doi.org/10.1109/icassp.2013.6639002","mag":"1997035035"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"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":true,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, US","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, US","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737161","display_name":"Lu\u00eds Oliveira","orcid":"https://orcid.org/0000-0002-9024-2200"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis C. Oliveira","raw_affiliation_strings":["L2F Spoken Language Systems Lab, INESC-ID / IST Lisboa, Portugal","L2F Spoken Language Syst. Lab., INESC-ID / IST Lisboa, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L2F Spoken Language Systems Lab, INESC-ID / IST Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"L2F Spoken Language Syst. Lab., INESC-ID / IST Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"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":"Alan W Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068922218"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4942,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75519681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"6915","last_page":"6919"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.996999979019165,"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/phrase","display_name":"Phrase","score":0.7997517585754395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719228982925415},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6852568984031677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6286699175834656},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5986635088920593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540044903755188},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5007326602935791},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4572529196739197},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4390344023704529},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4210391640663147},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41307780146598816},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41040271520614624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32299190759658813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13744798302650452}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7997517585754395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719228982925415},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6852568984031677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6286699175834656},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5986635088920593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540044903755188},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5007326602935791},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4572529196739197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4390344023704529},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4210391640663147},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41307780146598816},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41040271520614624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32299190759658813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13744798302650452},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.9033","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.9033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~gopalakr/publications/stylef0vc_icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W4927070","https://openalex.org/W23142961","https://openalex.org/W202879582","https://openalex.org/W1570629387","https://openalex.org/W2093414802","https://openalex.org/W2100649345","https://openalex.org/W2112390707","https://openalex.org/W2120605154","https://openalex.org/W2244925781","https://openalex.org/W2295027170","https://openalex.org/W6600209388"],"related_works":["https://openalex.org/W2076792495","https://openalex.org/W2054619580","https://openalex.org/W2792721393","https://openalex.org/W1724187744","https://openalex.org/W2956087996","https://openalex.org/W2553358787","https://openalex.org/W2154644810","https://openalex.org/W154086444","https://openalex.org/W2599068449","https://openalex.org/W335559838"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,29,59],"present":[4],"a":[5,31,69,80,125,152],"new":[6],"approach":[7],"to":[8,74,131],"F0":[9,77,88,140],"transformation,":[10,28],"that":[11,33,106,142],"can":[12],"capture":[13],"aspects":[14],"of":[15,19,55],"speaking":[16],"style.":[17],"Instead":[18],"using":[20,119],"the":[21,49,76,87,96,103,108,116,133,148],"traditional":[22],"5ms":[23],"frames":[24],"as":[25,40],"units":[26],"in":[27,48,64],"propose":[30],"method":[32,138],"looks":[34],"at":[35],"longer":[36],"phonological":[37,62],"regions":[38],"such":[39],"metrical":[41,46],"feet.":[42],"We":[43,67,114,123],"automatically":[44],"detect":[45],"feet":[47,93],"source":[50,56,97],"speech,":[51],"and":[52,98],"for":[53,86,95,111],"each":[54,92],"speaker's":[57],"feet,":[58],"find":[60],"its":[61],"correspondence":[63],"target":[65,99,149],"speech.":[66],"use":[68,124],"statistical":[70],"phrase":[71,117],"accent":[72,134],"model":[73,130],"represent":[75],"contour,":[78],"where":[79],"4-dimensional":[81],"TILT":[82],"representation":[83],"is":[84,89,107],"used":[85],"parameterized":[90],"over":[91],"region":[94],"speakers.":[100],"This":[101],"forms":[102],"parallel":[104],"data":[105,110],"training":[109],"our":[112],"transformation.":[113],"transform":[115,132],"component":[118],"simple":[120],"z-score":[121],"mapping.":[122],"joint":[126],"density":[127],"Gaussian":[128],"mixture":[129],"contours.":[135],"Our":[136],"transformation":[137],"generates":[139],"contours":[141],"are":[143],"significantly":[144],"more":[145],"correlated":[146],"with":[147],"speech":[150],"than":[151],"baseline,":[153],"frame-based":[154],"method.":[155]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}