{"id":"https://openalex.org/W2785516183","doi":"https://doi.org/10.1109/asru.2017.8269005","title":"Subband wavenet with overlapped single-sideband filterbanks","display_name":"Subband wavenet with overlapped single-sideband filterbanks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785516183","doi":"https://doi.org/10.1109/asru.2017.8269005","mag":"2785516183"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269005","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100925892","display_name":"Kentaro Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Tachibana","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109350986","display_name":"Yoshinori Shiga","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Shiga","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7168187499046326},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6643431782722473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6326997876167297},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6030438542366028},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5580191016197205},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5575980544090271},{"id":"https://openalex.org/keywords/sideband","display_name":"Sideband","score":0.5360335111618042},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5032581686973572},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4759347438812256},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3834821283817291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34663355350494385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357637822628021},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3275536298751831},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12484374642372131},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11551916599273682},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.10394290089607239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7168187499046326},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6643431782722473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6326997876167297},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6030438542366028},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5580191016197205},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5575980544090271},{"id":"https://openalex.org/C2776499502","wikidata":"https://www.wikidata.org/wiki/Q2267009","display_name":"Sideband","level":3,"score":0.5360335111618042},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5032581686973572},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4759347438812256},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3834821283817291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34663355350494385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357637822628021},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3275536298751831},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12484374642372131},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11551916599273682},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.10394290089607239},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8269005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269005","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1481646516","https://openalex.org/W1522301498","https://openalex.org/W1527535554","https://openalex.org/W1563460361","https://openalex.org/W1963637322","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2294797155","https://openalex.org/W2338186431","https://openalex.org/W2395849284","https://openalex.org/W2417163358","https://openalex.org/W2471520273","https://openalex.org/W2507771204","https://openalex.org/W2508073380","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2592040118","https://openalex.org/W2749651610","https://openalex.org/W2789740382","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2963609956","https://openalex.org/W2964115871","https://openalex.org/W2964121744","https://openalex.org/W2964301388","https://openalex.org/W3151844557","https://openalex.org/W6631190155","https://openalex.org/W6675380101","https://openalex.org/W6696843773","https://openalex.org/W6732429163","https://openalex.org/W6734815144","https://openalex.org/W6736734616","https://openalex.org/W6748674297","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2965983352","https://openalex.org/W1924629901","https://openalex.org/W1980759281","https://openalex.org/W4309103148","https://openalex.org/W3144702526","https://openalex.org/W2784222102","https://openalex.org/W2053531689","https://openalex.org/W1842536210","https://openalex.org/W2109142991","https://openalex.org/W2350061705"],"abstract_inverted_index":{"Compared":[0],"with":[1,30,49,68,110,123],"conventional":[2,149],"vocoders,":[3],"deep":[4],"neural":[5],"network-based":[6],"raw":[7,50],"audio":[8,51],"generative":[9,52],"models,":[10],"such":[11],"as":[12],"WaveNet":[13,38,76,109,122],"and":[14,46,62,73,93,104,140],"SampleRNN,":[15],"can":[16,132],"more":[17,146],"naturally":[18],"synthesize":[19],"speech":[20,58,98,144],"signals,":[21],"although":[22],"the":[23,55,85,119,137,142,148],"synthesis":[24,48,86,138],"speed":[25,139],"is":[26,78,91],"a":[27,69,96,111,124],"problem,":[28],"especially":[29],"high":[31],"sampling":[32,71,112],"frequency.":[33],"This":[34],"paper":[35],"provides":[36],"subband":[37,65,75,82,121],"based":[39],"on":[40],"multirate":[41],"signal":[42,90],"processing":[43],"for":[44,107],"high-speed":[45],"high-quality":[47],"models.":[53],"In":[54,84],"training":[56],"stage,":[57,87],"waveforms":[59,67],"are":[60],"decomposed":[61],"decimated":[63],"into":[64,95],"short":[66],"low":[70],"rate,":[72],"each":[74,81,88],"network":[77],"trained":[79],"using":[80],"stream.":[83],"generated":[89],"up-sampled":[92],"integrated":[94],"fullband":[97,150],"signal.":[99],"The":[100],"results":[101],"of":[102,114],"objective":[103],"subjective":[105],"experiments":[106],"unconditional":[108],"frequency":[113],"32":[115],"kHz":[116],"indicate":[117],"that":[118],"proposed":[120],"square-root":[125],"Hann":[126],"window-based":[127],"overlapped":[128],"9-channel":[129],"single-sideband":[130],"filterbank":[131],"realize":[133],"about":[134],"four":[135],"times":[136],"improve":[141],"synthesized":[143],"quality":[145],"than":[147],"WaveNet.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}