{"id":"https://openalex.org/W2136597038","doi":"https://doi.org/10.1109/icassp.2014.6854320","title":"Complex cepstrum factorization for statistical parametric synthesis","display_name":"Complex cepstrum factorization for statistical parametric synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2136597038","doi":"https://doi.org/10.1109/icassp.2014.6854320","mag":"2136597038"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6916,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88174793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"e85 d","issue":null,"first_page":"3839","last_page":"3843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9993000030517578,"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/cepstrum","display_name":"Cepstrum","score":0.9721670150756836},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7509118318557739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6549444794654846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5990889072418213},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5904870629310608},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5817168951034546},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.552466630935669},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.45410192012786865},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.42980071902275085},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4225016236305237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3904111385345459},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2615566849708557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.207038015127182},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.15670520067214966},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07418838143348694}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.9721670150756836},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7509118318557739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549444794654846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5990889072418213},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5904870629310608},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5817168951034546},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.552466630935669},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.45410192012786865},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.42980071902275085},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4225016236305237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3904111385345459},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2615566849708557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.207038015127182},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.15670520067214966},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07418838143348694},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W153193638","https://openalex.org/W1493163583","https://openalex.org/W1512429158","https://openalex.org/W1663973292","https://openalex.org/W1766888123","https://openalex.org/W1948357167","https://openalex.org/W1990826500","https://openalex.org/W2025920047","https://openalex.org/W2042946036","https://openalex.org/W2092619565","https://openalex.org/W2098039850","https://openalex.org/W2116808668","https://openalex.org/W2120649056","https://openalex.org/W2128413412","https://openalex.org/W2150619194","https://openalex.org/W2168161684","https://openalex.org/W2401881555","https://openalex.org/W2481593960","https://openalex.org/W3109938142","https://openalex.org/W4212863985","https://openalex.org/W6630838124","https://openalex.org/W6637883433","https://openalex.org/W6713081056"],"related_works":["https://openalex.org/W2100012411","https://openalex.org/W1482212662","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W3044927199","https://openalex.org/W2102353451","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"study":[4],"on":[5],"complex":[6,36,46,93],"cepstrum-based":[7],"speech":[8],"factorization":[9,18],"for":[10],"acoustic":[11,50],"modeling":[12],"in":[13,48,56,88],"statistical":[14],"parametric":[15],"synthesizers.":[16],"The":[17],"is":[19],"conducted":[20],"assuming":[21],"that":[22],"both":[23],"vocal":[24],"tract":[25],"resonance":[26],"and":[27,52,63,66,79],"glottal":[28],"flow":[29],"effect":[30],"are":[31,84],"fully":[32],"represented":[33],"by":[34],"the":[35,45,49,70,77,85,92,97],"cepstrum.":[37],"We":[38],"investigated":[39],"four":[40],"different":[41],"forms":[42],"to":[43,74],"represent":[44],"cepstrum":[47,82,94],"models":[51],"compared":[53],"their":[54],"performances":[55],"terms":[57,89],"of":[58,69,90],"objective":[59],"measures":[60],"between":[61],"reconstructed":[62],"natural":[64],"waveforms":[65],"final":[67],"quality":[68],"synthesized":[71],"speech.":[72],"According":[73],"experimental":[75],"results,":[76],"all-pass/minimum-phase":[78],"real":[80],"cepstrum/phase":[81],"decompositions":[83],"best":[86],"ones":[87],"preserving":[91],"information":[95],"after":[96],"parameter":[98],"generation":[99],"process.":[100]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}