{"id":"https://openalex.org/W4224920350","doi":"https://doi.org/10.1109/icassp43922.2022.9747318","title":"Minimizing Residuals for Native-Nonnative Voice Conversion in a Sparse, Anchor-Based Representation of Speech","display_name":"Minimizing Residuals for Native-Nonnative Voice Conversion in a Sparse, Anchor-Based Representation of Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920350","doi":"https://doi.org/10.1109/icassp43922.2022.9747318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747318","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5077682246","display_name":"Christopher Liberatore","orcid":"https://orcid.org/0000-0002-5871-0596"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Liberatore","raw_affiliation_strings":["Texas A&M University,College Station,Texas,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,College Station,Texas,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062423099","display_name":"Ricardo Guti\u00e9rrez\u2010Osuna","orcid":"https://orcid.org/0000-0003-2817-2085"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Gutierrez-Osuna","raw_affiliation_strings":["Texas A&M University,College Station,Texas,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,College Station,Texas,USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02279353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"series b","issue":null,"first_page":"7002","last_page":"7006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9828000068664551,"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/residual","display_name":"Residual","score":0.78766930103302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721030712127686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6365035772323608},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.5924204587936401},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5816716551780701},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5476294755935669},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5044280290603638},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4181487560272217},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41160714626312256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40085655450820923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3848514258861542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3714538812637329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13021355867385864},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06603094935417175}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.78766930103302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721030712127686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6365035772323608},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.5924204587936401},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5816716551780701},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5476294755935669},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5044280290603638},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4181487560272217},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41160714626312256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40085655450820923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3848514258861542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3714538812637329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13021355867385864},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06603094935417175},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747318","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W93060608","https://openalex.org/W95152782","https://openalex.org/W116902681","https://openalex.org/W1576602419","https://openalex.org/W1965912016","https://openalex.org/W1977362459","https://openalex.org/W2004299580","https://openalex.org/W2017742648","https://openalex.org/W2020304287","https://openalex.org/W2022241205","https://openalex.org/W2063978378","https://openalex.org/W2112447569","https://openalex.org/W2115429828","https://openalex.org/W2120605154","https://openalex.org/W2125047278","https://openalex.org/W2135046866","https://openalex.org/W2152205330","https://openalex.org/W2169878657","https://openalex.org/W2292984643","https://openalex.org/W2400588950","https://openalex.org/W2577042574","https://openalex.org/W2675443237","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2955237921","https://openalex.org/W2983786745","https://openalex.org/W3201403628","https://openalex.org/W6603807496","https://openalex.org/W6603838645","https://openalex.org/W6604828220","https://openalex.org/W6676727762","https://openalex.org/W6732251480"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W4205656132","https://openalex.org/W2111634407","https://openalex.org/W3004790527","https://openalex.org/W2203155458","https://openalex.org/W2783282829","https://openalex.org/W2138494306","https://openalex.org/W2539392819","https://openalex.org/W212310357"],"abstract_inverted_index":{"We":[0,44,103],"present":[1],"a":[2,60],"dictionary-learning":[3],"algorithm":[4,22,67,92,109],"for":[5,15,110],"reducing":[6],"the":[7,25,34,46,51,78,90,96,100,105,108],"sparse":[8],"coding":[9],"residual":[10,35,101],"of":[11,77,85,107],"an":[12],"exemplar-based":[13,62,112],"method":[14,47],"native-to-nonnative":[16],"voice":[17,37],"conversion":[18,38],"(VC).":[19],"The":[20,65],"proposed":[21,66,91],"iteratively":[23],"updates":[24],"source":[26],"and":[27,36,53,56,99],"target":[28],"speaker":[29],"dictionaries":[30],"to":[31,59,72],"reduce":[32],"both":[33,95],"error,":[39],"thereby":[40],"increasing":[41],"synthesis":[42,70],"quality.":[43],"evaluate":[45],"on":[48],"speech":[49],"from":[50],"ARCTIC":[52],"L2-ARCTIC":[54],"corpora":[55],"compare":[57],"it":[58],"baseline":[61,79],"VC":[63,97,113],"algorithm.":[64],"significantly":[68,93],"improves":[69],"quality":[71],"more":[73],"than":[74],"double":[75],"that":[76],"system":[80],"while":[81],"using":[82],"two":[83],"orders":[84],"magnitude":[86],"fewer":[87],"atoms.":[88],"Additionally,":[89],"reduces":[94],"error":[98],"magnitude.":[102],"discuss":[104],"implications":[106],"broad":[111],"systems.":[114]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}