{"id":"https://openalex.org/W2164028031","doi":"https://doi.org/10.1109/icassp.2008.4518696","title":"Voice conversion by combining frequency warping with unit selection","display_name":"Voice conversion by combining frequency warping with unit selection","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2164028031","doi":"https://doi.org/10.1109/icassp.2008.4518696","mag":"2164028031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518696","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5071906610","display_name":"Zhiwei Shuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiwei Shuang","raw_affiliation_strings":["IBM China Research Laboratory, China"],"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047324613","display_name":"Fanping Meng","orcid":"https://orcid.org/0000-0002-6172-2969"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanping Meng","raw_affiliation_strings":["IBM China Research Laboratory, China"],"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["IBM China Research Laboratory, China"],"affiliations":[{"raw_affiliation_string":"IBM China Research Laboratory, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071906610"],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":1.503,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8150358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4661","last_page":"4664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9958000183105469,"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/image-warping","display_name":"Image warping","score":0.7936965227127075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368723750114441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7148950099945068},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6268249154090881},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5669893026351929},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5597302913665771},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46764513850212097},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.43261459469795227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40494561195373535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36031824350357056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07940918207168579},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06351089477539062}],"concepts":[{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7936965227127075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368723750114441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7148950099945068},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6268249154090881},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5669893026351929},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5597302913665771},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46764513850212097},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.43261459469795227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40494561195373535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36031824350357056},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07940918207168579},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06351089477539062},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518696","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W31448757","https://openalex.org/W1533098358","https://openalex.org/W1963778986","https://openalex.org/W2103783707","https://openalex.org/W2105698384","https://openalex.org/W2114659828","https://openalex.org/W2118850452","https://openalex.org/W2140567543","https://openalex.org/W2143116775","https://openalex.org/W2156142001","https://openalex.org/W2244925781","https://openalex.org/W2398319638","https://openalex.org/W2405069075","https://openalex.org/W6601280771","https://openalex.org/W6653852971","https://openalex.org/W6902064130"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2735770592","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"novel":[6],"voice":[7,92],"conversion":[8,93],"method":[9,100],"by":[10,70],"combining":[11],"frequency":[12,26,112],"warping":[13,27],"and":[14],"unit":[15,43],"selection":[16,44],"to":[17,21,28,82,110],"improve":[18],"the":[19,30,46,55,64,71,79,84,98],"similarity":[20,107],"target":[22,40,47,52,73],"speaker.":[23],"We":[24],"use":[25],"get":[29],"warped":[31,65],"source":[32,66],"spectrum,":[33],"which":[34],"will":[35],"be":[36],"used":[37],"as":[38],"estimated":[39,51],"for":[41],"later":[42],"of":[45,58,63],"speaker's":[48,74],"spectrum.":[49,88],"Such":[50],"can":[53,101],"preserve":[54],"natural":[56],"transition":[57],"human's":[59],"speech.":[60],"Then,":[61],"part":[62],"spectrum":[67,76],"is":[68],"replaced":[69],"selected":[72],"real":[75],"before":[77],"reconstructing":[78],"converted":[80],"speech":[81],"reduce":[83],"difference":[85],"in":[86,106],"detailed":[87],"TC-":[89],"STAR":[90],"2007":[91],"evaluation":[94],"results":[95],"show":[96],"that":[97],"proposed":[99],"achieve":[102],"about":[103],"20%":[104],"improvement":[105],"score":[108],"compared":[109],"only":[111],"warping.":[113]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
