{"id":"https://openalex.org/W1518567289","doi":"https://doi.org/10.21437/interspeech.2004-444","title":"Including dynamic and phonetic information in voice conversion systems","display_name":"Including dynamic and phonetic information in voice conversion systems","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1518567289","doi":"https://doi.org/10.21437/interspeech.2004-444","mag":"1518567289"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Polytechnic University of Catalonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066668295","display_name":"Alexander Kain","orcid":"https://orcid.org/0000-0001-5807-9311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Kain","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041808115","display_name":"Jan P. H. van Santen","orcid":"https://orcid.org/0000-0003-3245-5301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan van Santen","raw_affiliation_strings":["Institute on Development & Disability"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute on Development & Disability","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058383534","display_name":"Helenca Duxans","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Helenca Duxans","raw_affiliation_strings":["Polytechnic University of Catalonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1193","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9990000128746033,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7919554710388184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7542017698287964},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.653434693813324},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5565118193626404},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5397833585739136},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.490389347076416},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45603621006011963},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.44024574756622314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3701898455619812},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09000670909881592},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.057649582624435425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919554710388184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7542017698287964},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.653434693813324},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5565118193626404},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5397833585739136},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.490389347076416},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45603621006011963},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.44024574756622314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3701898455619812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09000670909881592},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.057649582624435425},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1526513105","https://openalex.org/W1570450547","https://openalex.org/W1592940279","https://openalex.org/W1892640180","https://openalex.org/W2033641795","https://openalex.org/W2111550316","https://openalex.org/W2123003832"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1980742206","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362","https://openalex.org/W2136153680"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"systems":[3],"modify":[4],"a":[5,35],"speaker":[6,16,66],"voice":[7],"(source":[8],"speaker)":[9,18],"to":[10,52,63,76],"be":[11],"perceived":[12],"as":[13],"if":[14],"another":[15],"(target":[17],"had":[19],"uttered":[20],"it.":[21],"Previous":[22],"published":[23],"VC":[24,56,90],"approaches":[25,47],"using":[26,38],"Gaussian":[27],"Mixture":[28],"Models":[29],"[1]":[30],"performs":[31],"the":[32,54,65,70,86,89,97,100],"conversion":[33],"in":[34,50,85],"frame-by-frame":[36],"basis":[37],"only":[39],"spectral":[40],"information.":[41],"In":[42],"this":[43],"paper,":[44],"two":[45],"new":[46],"are":[48],"studied":[49],"order":[51],"extend":[53],"GMM-based":[55],"systems.":[57,102],"First,":[58],"dynamic":[59],"information":[60,82],"is":[61,72,83],"used":[62],"build":[64],"acoustic":[67],"model.":[68],"So,":[69],"transformation":[71],"carried":[73],"out":[74],"according":[75],"sequences":[77],"of":[78,88,99],"frames.":[79],"Then,":[80],"phonetic":[81],"introduced":[84],"training":[87],"system.":[91],"Objective":[92],"and":[93],"perceptual":[94],"results":[95],"compare":[96],"performance":[98],"proposed":[101]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
