{"id":"https://openalex.org/W2407398888","doi":"https://doi.org/10.1109/icassp.2016.7472661","title":"Multi-stream spectral representation for statistical parametric speech synthesis","display_name":"Multi-stream spectral representation for statistical parametric speech synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407398888","doi":"https://doi.org/10.1109/icassp.2016.7472661","mag":"2407398888"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"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":true,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge Research Lab, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge Research Lab, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","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 Ltd, Cambridge Research Lab, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge Research Lab, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","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":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge Research Lab, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge Research Lab, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047287498"],"corresponding_institution_ids":["https://openalex.org/I4210143477"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02658916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5160","last_page":"5164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9909999966621399,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7873824834823608},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7461304664611816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6895063519477844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6523517370223999},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6268715262413025},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5923458337783813},{"id":"https://openalex.org/keywords/radio-spectrum","display_name":"Radio spectrum","score":0.4301924705505371},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42794737219810486},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4200670123100281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3616410493850708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3384334444999695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25512778759002686},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13013461232185364},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0831642746925354}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7873824834823608},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7461304664611816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6895063519477844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523517370223999},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6268715262413025},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5923458337783813},{"id":"https://openalex.org/C92545706","wikidata":"https://www.wikidata.org/wiki/Q902174","display_name":"Radio spectrum","level":2,"score":0.4301924705505371},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42794737219810486},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4200670123100281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3616410493850708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3384334444999695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25512778759002686},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13013461232185364},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0831642746925354},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W198801378","https://openalex.org/W963310052","https://openalex.org/W1484695120","https://openalex.org/W1493982694","https://openalex.org/W1532880163","https://openalex.org/W1542318757","https://openalex.org/W1550869207","https://openalex.org/W1569690071","https://openalex.org/W1843883989","https://openalex.org/W1963627370","https://openalex.org/W1973766695","https://openalex.org/W1982146801","https://openalex.org/W2082388554","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2148428486","https://openalex.org/W2149768386","https://openalex.org/W2157259375","https://openalex.org/W2158972663","https://openalex.org/W2199472667","https://openalex.org/W2210794830","https://openalex.org/W2212186116","https://openalex.org/W2260464745","https://openalex.org/W2275391315","https://openalex.org/W2292221303","https://openalex.org/W2294881479","https://openalex.org/W2311697212","https://openalex.org/W2331493012","https://openalex.org/W2346077187","https://openalex.org/W2401570946","https://openalex.org/W2402552913","https://openalex.org/W2405715270","https://openalex.org/W2408267635","https://openalex.org/W2733190194","https://openalex.org/W2922672734","https://openalex.org/W3099525924","https://openalex.org/W6683276001","https://openalex.org/W6713259303","https://openalex.org/W6713427754"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W1978572805","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2383807498","https://openalex.org/W2025614924","https://openalex.org/W1997992934","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"In":[0,33],"statistical":[1],"parametric":[2],"speech":[3,84],"synthesis":[4,93],"such":[5],"as":[6,74,78,80],"Hidden":[7],"Markov":[8],"Model":[9],"(HMM)":[10],"based":[11],"synthesis,":[12],"one":[13],"of":[14,21],"the":[15,19,30,42,50,103,110,121],"problems":[16],"is":[17,46,65,106],"in":[18,29,40],"over-smoothing":[20],"parameters,":[22],"which":[23,41,58],"leads":[24],"to":[25,75,82],"a":[26,68,114],"muffled":[27,126],"sensation":[28],"synthesised":[31,119],"output.":[32],"this":[34],"paper,":[35],"we":[36],"propose":[37],"an":[38],"approach":[39,105,112,123],"high":[43,55],"frequency":[44,52,56,88],"spectrum":[45,116],"modelled":[47],"separately":[48],"from":[49],"low":[51],"spectrum.":[53],"The":[54,86],"band,":[57],"does":[59],"not":[60],"carry":[61],"much":[62],"linguistic":[63],"information,":[64],"clustered":[66],"using":[67,113,120],"very":[69],"large":[70],"decision":[71],"tree":[72],"so":[73],"generate":[76],"parameters":[77],"close":[79],"possible":[81],"natural":[83],"samples.":[85],"boundary":[87],"can":[89],"be":[90],"adjusted":[91],"at":[92],"time":[94],"for":[95],"each":[96],"state.":[97],"Subjective":[98],"listening":[99],"tests":[100],"show":[101],"that":[102],"proposed":[104,122],"significantly":[107],"preferred":[108],"over":[109],"conventional":[111],"single":[115],"stream.":[117],"Samples":[118],"sound":[124],"less":[125],"and":[127],"more":[128],"natural.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}