{"id":"https://openalex.org/W2128766084","doi":"https://doi.org/10.1109/icassp.2005.1415038","title":"A Study on Residual Prediction Techniques for Voice Conversion","display_name":"A Study on Residual Prediction Techniques for Voice Conversion","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2128766084","doi":"https://doi.org/10.1109/icassp.2005.1415038","mag":"2128766084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5112145013","display_name":"David Suendermann","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":true,"raw_author_name":"D. Suendermann","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","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":"A. Bonafonte","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"H. Ney","raw_affiliation_strings":["Computer Science Department, RWTH Aachen - University of Technology, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, RWTH Aachen - University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061781359","display_name":"Harald H\u00f6ege","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"H. Hoege","raw_affiliation_strings":["Computer Science Department, RWTH Aachen - University of Technology, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, RWTH Aachen - University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112145013"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":6.0423,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96870332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"13","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9932000041007996,"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":0.9513999819755554,"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/residual","display_name":"Residual","score":0.8535776138305664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7321815490722656},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.6445826292037964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6146011352539062},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5487658381462097},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46120020747184753},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4134112596511841},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2702740430831909},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07716569304466248}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8535776138305664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7321815490722656},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.6445826292037964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6146011352539062},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5487658381462097},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46120020747184753},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4134112596511841},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2702740430831909},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07716569304466248}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W129217914","https://openalex.org/W1518567289","https://openalex.org/W1520370180","https://openalex.org/W1526513105","https://openalex.org/W1535259248","https://openalex.org/W2110589840","https://openalex.org/W2143116775","https://openalex.org/W2148228080","https://openalex.org/W2405069075","https://openalex.org/W4231951313","https://openalex.org/W6605232188","https://openalex.org/W6676465519"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W3094412894","https://openalex.org/W2809253131","https://openalex.org/W1562592894","https://openalex.org/W2778699561","https://openalex.org/W2097038718","https://openalex.org/W2541144433","https://openalex.org/W2375172098","https://openalex.org/W2217785378","https://openalex.org/W2128766084"],"abstract_inverted_index":{"Several":[0],"well-studied":[1],"voice":[2,66,81],"conversion":[3,82],"techniques":[4],"use":[5],"line":[6],"spectral":[7,14],"frequencies":[8],"as":[9,39],"features":[10,30],"to":[11,23,25,33,45],"represent":[12],"the":[13,17,26,62,76],"envelopes":[15],"of":[16,41,80],"processed":[18],"speech":[19],"frames.":[20],"In":[21],"order":[22],"return":[24],"time":[27],"domain,":[28],"these":[29],"are":[31],"converted":[32],"linear":[34],"predictive":[35],"coefficients":[36,40],"that":[37,56,74],"serve":[38],"a":[42,71],"filter":[43],"applied":[44],"an":[46],"unknown":[47],"residual":[48,53],"signal.":[49],"We":[50,68],"compare":[51],"several":[52],"prediction":[54],"approaches":[55],"have":[57],"already":[58],"been":[59],"proposed":[60],"in":[61,78],"literature":[63],"dealing":[64],"with":[65],"conversion.":[67],"also":[69],"present":[70],"novel":[72],"technique":[73],"outperforms":[75],"others":[77],"terms":[79],"performance":[83],"and":[84],"sound":[85],"quality.":[86]},"counts_by_year":[{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
