{"id":"https://openalex.org/W4406860166","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848612","title":"Gamma-VAE: Speech representation based on VAE assuming gamma distribution for both latent variables and observation","display_name":"Gamma-VAE: Speech representation based on VAE assuming gamma distribution for both latent variables and observation","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860166","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848612"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5116047153","display_name":"Nanako Imaichi","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nanako Imaichi","raw_affiliation_strings":["University of Electro-Communication,Chofu, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communication,Chofu, Tokyo","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065514143","display_name":"Toru Nakashika","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["University of Electro-Communication,Chofu, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communication,Chofu, Tokyo","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6177671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9645000100135803,"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/T12031","display_name":"Speech and dialogue systems","score":0.9190000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6069530844688416},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6023105978965759},{"id":"https://openalex.org/keywords/gamma-distribution","display_name":"Gamma distribution","score":0.5837700366973877},{"id":"https://openalex.org/keywords/generalized-gamma-distribution","display_name":"Generalized gamma distribution","score":0.5313147902488708},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5228605270385742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39775678515434265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38055458664894104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38046061992645264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2625654935836792},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22444882988929749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069530844688416},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6023105978965759},{"id":"https://openalex.org/C149717495","wikidata":"https://www.wikidata.org/wiki/Q117806","display_name":"Gamma distribution","level":2,"score":0.5837700366973877},{"id":"https://openalex.org/C42337464","wikidata":"https://www.wikidata.org/wiki/Q5532478","display_name":"Generalized gamma distribution","level":3,"score":0.5313147902488708},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5228605270385742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39775678515434265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38055458664894104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38046061992645264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2625654935836792},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22444882988929749},{"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/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/apsipaasc63619.2025.10848612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W95630922","https://openalex.org/W1552314771","https://openalex.org/W2042492924","https://openalex.org/W2064675550","https://openalex.org/W2100495367","https://openalex.org/W2120847449","https://openalex.org/W2135346645","https://openalex.org/W2141998673","https://openalex.org/W2194775991","https://openalex.org/W2752796333","https://openalex.org/W2947590261","https://openalex.org/W3092028330","https://openalex.org/W3182478434","https://openalex.org/W4225956675","https://openalex.org/W4312933868","https://openalex.org/W4365512576","https://openalex.org/W6680012447","https://openalex.org/W6739922093","https://openalex.org/W6838437557"],"related_works":["https://openalex.org/W4229773611","https://openalex.org/W4256284424","https://openalex.org/W2971192015","https://openalex.org/W4233558325","https://openalex.org/W1991526242","https://openalex.org/W2939669598","https://openalex.org/W4226383454","https://openalex.org/W1964921333","https://openalex.org/W2146035246","https://openalex.org/W2328340313"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"deep":[3],"generative":[4],"models":[5],"that":[6,106,114],"can":[7],"represent":[8],"complex":[9],"relationships":[10],"in":[11,69],"data":[12],"generation":[13],"have":[14],"attracted":[15],"significant":[16],"attention.":[17],"One":[18],"example":[19],"is":[20,53,58,67,77,103],"the":[21,33,50,63,70,92,100,125,143],"variational":[22],"autoencoder":[23],"(VAE),":[24],"which":[25,102,128],"usually":[26],"assumes":[27,107,130],"a":[28,59,74,82,104,108,111,120,131],"Gaussian":[29,75,83],"distribution":[30,76,84,113,133],"for":[31,134],"both":[32],"encoder":[34],"and":[35,37,66,119],"decoder":[36],"often":[38],"utilizes":[39],"amplitude":[40,51,89],"spectra":[41,90],"because":[42,56],"they":[43],"are":[44],"suitable":[45],"as":[46,91],"input":[47,93],"features.":[48,94],"However,":[49],"spectrum":[52],"always":[54],"positive":[55,117],"it":[57],"Fourier":[60],"transform":[61],"of":[62,122,145],"aperiodic":[64],"waveform":[65],"taken":[68],"absolute":[71],"value.":[72],"Thus,":[73],"not":[78],"appropriate":[79],"to":[80],"assume":[81],"when":[85],"using":[86,138],"VAE":[87,105],"with":[88],"As":[95],"an":[96],"alternative,":[97],"we":[98],"propose":[99],"Gamma-VAE,":[101],"gamma":[109,132],"distribution;":[110],"probability":[112],"considers":[115],"only":[116],"values;":[118],"method":[121],"back-propagation":[123],"by":[124],"reparameterization":[126],"trick,":[127],"also":[129],"latent":[135],"variables.":[136],"Experiments":[137],"various":[139],"evaluation":[140],"methods":[141],"showed":[142],"effectiveness":[144],"Gamma-VAE.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}