{"id":"https://openalex.org/W3007585125","doi":"https://doi.org/10.1109/asru46091.2019.9003800","title":"Investigation of Shallow Wavenet Vocoder with Laplacian Distribution Output","display_name":"Investigation of Shallow Wavenet Vocoder with Laplacian Distribution Output","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007585125","doi":"https://doi.org/10.1109/asru46091.2019.9003800","mag":"3007585125"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003800","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 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":"2019 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/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":null,"first_page":"176","last_page":"183"},"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":0.9994999766349792,"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":0.9954000115394592,"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/softmax-function","display_name":"Softmax function","score":0.788585901260376},{"id":"https://openalex.org/keywords/laplace-operator","display_name":"Laplace operator","score":0.7024278044700623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6835874319076538},{"id":"https://openalex.org/keywords/laplace-distribution","display_name":"Laplace distribution","score":0.6264538764953613},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5629084706306458},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5136169791221619},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5023794174194336},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46681901812553406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4553866386413574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3192998468875885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.309169739484787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.246694415807724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1591552495956421},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11182114481925964},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0948534607887268}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.788585901260376},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.7024278044700623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6835874319076538},{"id":"https://openalex.org/C183057437","wikidata":"https://www.wikidata.org/wiki/Q671617","display_name":"Laplace distribution","level":3,"score":0.6264538764953613},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5629084706306458},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5136169791221619},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5023794174194336},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46681901812553406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4553866386413574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3192998468875885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.309169739484787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.246694415807724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1591552495956421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11182114481925964},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0948534607887268},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003800","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 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":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W20030414","https://openalex.org/W773905565","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1963637322","https://openalex.org/W2000337867","https://openalex.org/W2007643058","https://openalex.org/W2012086895","https://openalex.org/W2049686551","https://openalex.org/W2055379949","https://openalex.org/W2074854222","https://openalex.org/W2095705004","https://openalex.org/W2120605154","https://openalex.org/W2145768101","https://openalex.org/W2157331557","https://openalex.org/W2162096028","https://openalex.org/W2406654659","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2524251915","https://openalex.org/W2584032004","https://openalex.org/W2747070883","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2786868129","https://openalex.org/W2794725088","https://openalex.org/W2797310469","https://openalex.org/W2803229097","https://openalex.org/W2803595463","https://openalex.org/W2803714261","https://openalex.org/W2889329491","https://openalex.org/W2890983311","https://openalex.org/W2936002583","https://openalex.org/W2938983457","https://openalex.org/W2963035245","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964041258","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2973115941","https://openalex.org/W4245284779","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6600801376","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6650385207","https://openalex.org/W6652313071","https://openalex.org/W6674330103","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6753855596"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W1922506815","https://openalex.org/W4385495213","https://openalex.org/W2895178859","https://openalex.org/W4235974481","https://openalex.org/W4387031402","https://openalex.org/W4379539251","https://openalex.org/W3206245744","https://openalex.org/W2019494924"],"abstract_inverted_index":{"In":[0,48],"this":[1],"paper,":[2],"an":[3],"investigation":[4],"of":[5,24,34,55,60,101,126,138,145],"shallow":[6,99],"architecture":[7,27,103],"and":[8,42,76,122],"Laplacian":[9,61,66,127],"distribution":[10,62,67,128],"output":[11,63,129],"for":[12,87,147],"WaveNet":[13,26,56,102],"vocoder":[14],"trained":[15],"with":[16,39,73,112],"limited":[17,40,139],"training":[18,140],"data":[19,41],"is":[20,28,64,68],"presented.":[21],"The":[22,91],"use":[23,37,59,125],"shallower":[25],"proposed":[29,98],"to":[30,43,50,108],"accommodate":[31],"the":[32,45,53,58,80,97,109,117,124,132,148],"possibility":[33],"more":[35,85],"suitable":[36,86],"case":[38],"reduce":[44],"computation":[46,118],"time.":[47],"order":[49],"further":[51],"improve":[52],"modeling":[54],"vocoder,":[57],"proposed.":[65],"inherently":[69],"a":[70,143],"sparse":[71],"distribution,":[72],"higher":[74],"peak":[75],"fatter":[77],"tail":[78],"than":[79],"Gaussian,":[81],"which":[82],"might":[83],"be":[84],"speech":[88,133],"signal":[89],"modeling.":[90],"experimental":[92],"results":[93],"demonstrate":[94],"that:":[95],"1)":[96],"variant":[100],"gives":[104],"comparable":[105],"performance":[106],"compared":[107],"deep":[110],"one":[111],"softmax":[113],"output,":[114],"while":[115],"reducing":[116],"time":[119],"by":[120],"73%;":[121],"2)":[123],"consistently":[130],"improves":[131],"quality":[134],"in":[135],"various":[136],"amounts":[137],"data,":[141],"reaching":[142],"value":[144],"4.22":[146],"two":[149],"highest":[150],"mean":[151],"opinion":[152],"scores.":[153]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}