{"id":"https://openalex.org/W2523904137","doi":"https://doi.org/10.1587/transinf.2016slp0006","title":"Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model","display_name":"Statistical Bandwidth Extension for Speech Synthesis Based on Gaussian Mixture Model with Sub-Band Basis Spectrum Model","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2523904137","doi":"https://doi.org/10.1587/transinf.2016slp0006","mag":"2523904137"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2016slp0006","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0006","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0006/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0006/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"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":true,"raw_author_name":"Yamato OHTANI","raw_affiliation_strings":["Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation"],"affiliations":[{"raw_affiliation_string":"Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113811305","display_name":"Masatsune Tamura","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":"Masatsune TAMURA","raw_affiliation_strings":["Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation"],"affiliations":[{"raw_affiliation_string":"Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031552934","display_name":"Masahiro Morita","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":"Masahiro MORITA","raw_affiliation_strings":["Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation"],"affiliations":[{"raw_affiliation_string":"Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","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":["Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation"],"affiliations":[{"raw_affiliation_string":"Knowledge Media Laboratory, Corporate Research & Development Center, Toshiba Corporation","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018533235"],"corresponding_institution_ids":["https://openalex.org/I1292669757"],"apc_list":null,"apc_paid":null,"fwci":0.2522,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53822794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E99.D","issue":"10","first_page":"2481","last_page":"2489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9919000267982483,"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/bandwidth","display_name":"Bandwidth (computing)","score":0.741200864315033},{"id":"https://openalex.org/keywords/aperiodic-graph","display_name":"Aperiodic graph","score":0.6617723703384399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6450552940368652},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6301478743553162},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.5623084306716919},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5540621280670166},{"id":"https://openalex.org/keywords/frequency-band","display_name":"Frequency band","score":0.43523120880126953},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4346471428871155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4308212101459503},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.420118123292923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4023474156856537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3362257182598114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254326581954956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.307278037071228},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18734210729599},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15295341610908508},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.11201798915863037},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10835513472557068}],"concepts":[{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.741200864315033},{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.6617723703384399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450552940368652},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6301478743553162},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.5623084306716919},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5540621280670166},{"id":"https://openalex.org/C2778116611","wikidata":"https://www.wikidata.org/wiki/Q25110567","display_name":"Frequency band","level":3,"score":0.43523120880126953},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4346471428871155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4308212101459503},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.420118123292923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4023474156856537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3362257182598114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254326581954956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.307278037071228},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18734210729599},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15295341610908508},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.11201798915863037},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10835513472557068},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2016slp0006","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0006","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0006/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2016slp0006","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2016slp0006","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E99.D/10/E99.D_2016SLP0006/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2523904137.pdf","grobid_xml":"https://content.openalex.org/works/W2523904137.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W24638977","https://openalex.org/W49412823","https://openalex.org/W97829328","https://openalex.org/W204144752","https://openalex.org/W330787962","https://openalex.org/W1517841224","https://openalex.org/W1992277579","https://openalex.org/W1997763773","https://openalex.org/W2005768155","https://openalex.org/W2007023536","https://openalex.org/W2015060114","https://openalex.org/W2022125261","https://openalex.org/W2034562896","https://openalex.org/W2073021785","https://openalex.org/W2075665712","https://openalex.org/W2095723991","https://openalex.org/W2100285470","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2135708429","https://openalex.org/W2145889472","https://openalex.org/W2146423068","https://openalex.org/W2146952473","https://openalex.org/W2147152002","https://openalex.org/W2152250293","https://openalex.org/W2153057929","https://openalex.org/W2154304575","https://openalex.org/W2156142001","https://openalex.org/W2158972663","https://openalex.org/W2162743322","https://openalex.org/W2395578248","https://openalex.org/W2397254463","https://openalex.org/W2397379842","https://openalex.org/W2399742709","https://openalex.org/W2401114028"],"related_works":["https://openalex.org/W2037661079","https://openalex.org/W2339191433","https://openalex.org/W4220811941","https://openalex.org/W4298800952","https://openalex.org/W2803419934","https://openalex.org/W2360445617","https://openalex.org/W2104434539","https://openalex.org/W2066487630","https://openalex.org/W1512303388","https://openalex.org/W4321495303"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,12,18,30,70],"novel":[4],"statistical":[5],"bandwidth":[6,52,84,179],"extension":[7],"(BWE)":[8],"technique":[9],"based":[10,122],"on":[11,123],"Gaussian":[13],"mixture":[14],"model":[15,22],"(GMM)":[16],"and":[17,104,164,168,209],"sub-band":[19],"basis":[20],"spectrum":[21],"(SBM),":[23],"in":[24,34,79,214],"which":[25],"each":[26],"dimensional":[27],"component":[28,195],"represents":[29],"specific":[31],"acoustic":[32],"space":[33],"the":[35,43,54,58,65,83,88,94,97,119,124,133,142,145,150,154,174,178,185,193,198,203,207,210,215],"frequency":[36,51],"domain.":[37],"The":[38],"proposed":[39,66,175,216],"method":[40,160,176],"can":[41],"achieve":[42],"BWE":[44,128],"from":[45,60,76,114,136,153,197],"speech":[46,181],"data":[47,182],"with":[48,72],"an":[49],"arbitrary":[50],"whereas":[53],"conventional":[55],"methods":[56],"perform":[57],"conversion":[59],"fixed":[61],"narrow-band":[62,155,200],"data.":[63],"In":[64],"method,":[67],"we":[68,157],"train":[69],"GMM":[71,90,95],"SBM":[73,103,106,110,116,139],"parameters":[74],"extracted":[75,196],"full-band":[77,151,211],"spectra":[78,134,163],"advance.":[80],"According":[81],"to":[82,93,141,161],"of":[85,96,118,144,180],"input":[86,120,146],"signal,":[87],"trained":[89],"is":[91,129],"reconstructed":[92,125],"joint":[98],"probability":[99],"density":[100],"between":[101],"low-band":[102,115],"high-band":[105,109,138],"components.":[107,166],"Then":[108],"components":[111,117,140,213],"are":[112],"estimated":[113,137],"signal":[121,152,201],"GMM.":[126],"Finally,":[127],"achieved":[130],"by":[131],"adding":[132],"decoded":[135],"ones":[143],"signal.":[147],"To":[148],"construct":[149],"one,":[156],"apply":[158],"this":[159],"log-amplitude":[162,186],"aperiodic":[165,194,212],"Objective":[167],"subjective":[169],"evaluation":[170],"results":[171,189],"show":[172],"that":[173,192],"extends":[177],"robustly":[183],"for":[184],"spectra.":[187],"Experimental":[188],"also":[190],"indicate":[191],"upsampled":[199],"realizes":[202],"same":[204],"performance":[205],"as":[206],"restored":[208],"method.":[217]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
