{"id":"https://openalex.org/W2150619194","doi":"https://doi.org/10.1109/icassp.2012.6288938","title":"Complex cepstrum as phase information in statistical parametric speech synthesis","display_name":"Complex cepstrum as phase information in statistical parametric speech synthesis","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2150619194","doi":"https://doi.org/10.1109/icassp.2012.6288938","mag":"2150619194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/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"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba Corporation, Corporate Research and Development Center, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporation, Corporate Research and Development Center, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"M. J. F. Gales","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3074,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95586689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"4581","last_page":"4584"},"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":0.9991999864578247,"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":0.9937999844551086,"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":0.8999189138412476},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7685372829437256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7041007280349731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6797415614128113},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.614698052406311},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5897267460823059},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49867844581604004},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4956701993942261},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4923182725906372},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.48338356614112854},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4681691527366638},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4349157214164734},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.42408284544944763},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4153619408607483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37127286195755005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1739950180053711},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.1610032021999359},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10158345103263855},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08360350131988525},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08149737119674683},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08070284128189087}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.8999189138412476},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7685372829437256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041007280349731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6797415614128113},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.614698052406311},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5897267460823059},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49867844581604004},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4956701993942261},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4923182725906372},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.48338356614112854},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4681691527366638},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4349157214164734},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.42408284544944763},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4153619408607483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37127286195755005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1739950180053711},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1610032021999359},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10158345103263855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08360350131988525},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08149737119674683},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08070284128189087},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:521312","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/521312/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W153193638","https://openalex.org/W163616957","https://openalex.org/W169745891","https://openalex.org/W330787962","https://openalex.org/W1493163583","https://openalex.org/W1766888123","https://openalex.org/W2025920047","https://openalex.org/W2042691334","https://openalex.org/W2093450784","https://openalex.org/W2129142580","https://openalex.org/W2140348518","https://openalex.org/W2158972663","https://openalex.org/W3109938142","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W1494715773","https://openalex.org/W2111813998"],"abstract_inverted_index":{"Statistical":[0],"parametric":[1,61,98],"synthesizers":[2],"usually":[3],"rely":[4],"on":[5],"a":[6,13,19,65,113],"simplified":[7],"model":[8],"of":[9,38,51,74,84,112],"speech":[10,40,62,137],"production":[11],"where":[12],"minimum-phase":[14],"filter":[15],"is":[16,69,89],"driven":[17],"by":[18,47],"zero":[20],"or":[21],"random":[22],"phase":[23,57,79,93,105,125],"excitation":[24],"signal.":[25,41],"However,":[26],"this":[27,45],"procedure":[28],"does":[29],"not":[30],"take":[31],"into":[32],"account":[33],"the":[34,39,49,52,72,85,96,103,120,128],"natural":[35],"mixed-phase":[36],"characteristics":[37],"This":[42],"paper":[43],"addresses":[44],"issue":[46],"proposing":[48],"use":[50],"complex":[53,67,87],"cepstrum":[54,68,88],"for":[55],"modeling":[56],"information":[58,126],"in":[59,95,127,132],"statistical":[60,97],"synthesizers.":[63],"Here":[64],"frame-based":[66,86],"calculated":[70],"through":[71],"interpolation":[73],"pitch-synchronous":[75],"magnitude":[76],"and":[77,135],"unwrapped":[78],"spectra.":[80],"The":[81],"noncausal":[82],"part":[83],"then":[90],"modeled":[91],"as":[92],"features":[94],"synthesizer.":[99],"At":[100],"synthesis":[101],"time,":[102],"generated":[104],"parameters":[106],"are":[107],"used":[108],"to":[109],"derive":[110],"coefficients":[111],"glottal":[114],"filter.":[115],"Experimental":[116],"results":[117],"show":[118],"that":[119],"proposed":[121],"approach":[122],"effectively":[123],"embeds":[124],"synthetic":[129],"speech,":[130],"resulting":[131],"close-to-natural":[133],"waveforms":[134],"better":[136],"quality.":[138]},"counts_by_year":[{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}