{"id":"https://openalex.org/W2922391058","doi":"https://doi.org/10.1109/icassp.2019.8682797","title":"A Deep Generative Model of Speech Complex Spectrograms","display_name":"A Deep Generative Model of Speech Complex Spectrograms","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2922391058","doi":"https://doi.org/10.1109/icassp.2019.8682797","mag":"2922391058"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.03269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["RIKEN Center for Advanced Intelligence Project (AIP), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project (AIP), Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouhei Sekiguchi","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.962,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86599686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"909"},"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":0.9988999962806702,"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":0.9983000159263611,"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/spectrogram","display_name":"Spectrogram","score":0.8384513854980469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6129374504089355},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.580322802066803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47324830293655396},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4650975465774536},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4633534252643585},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44395965337753296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.413187175989151},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40049564838409424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3574759364128113},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32191407680511475},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2400132417678833},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1796145737171173}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8384513854980469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129374504089355},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.580322802066803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47324830293655396},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4650975465774536},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4633534252643585},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44395965337753296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.413187175989151},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40049564838409424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3574759364128113},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32191407680511475},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2400132417678833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1796145737171173},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.03269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03269","pdf_url":"https://arxiv.org/pdf/1903.03269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.03269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03269","pdf_url":"https://arxiv.org/pdf/1903.03269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1582774210","https://openalex.org/W1815076433","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W1965555277","https://openalex.org/W1992833709","https://openalex.org/W2020997493","https://openalex.org/W2092262399","https://openalex.org/W2095072097","https://openalex.org/W2099471712","https://openalex.org/W2120847449","https://openalex.org/W2132085292","https://openalex.org/W2141998673","https://openalex.org/W2284050935","https://openalex.org/W2345844407","https://openalex.org/W2401387233","https://openalex.org/W2480859021","https://openalex.org/W2504507112","https://openalex.org/W2519091744","https://openalex.org/W2559260703","https://openalex.org/W2559597482","https://openalex.org/W2567070169","https://openalex.org/W2766672686","https://openalex.org/W2792764867","https://openalex.org/W2803045109","https://openalex.org/W2874689226","https://openalex.org/W2883322837","https://openalex.org/W2886577208","https://openalex.org/W2889134433","https://openalex.org/W2894192904","https://openalex.org/W2918296821","https://openalex.org/W2922004249","https://openalex.org/W2949382160","https://openalex.org/W2963090522","https://openalex.org/W2963175398","https://openalex.org/W2963446712","https://openalex.org/W2963685250","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2982840733","https://openalex.org/W3100968126","https://openalex.org/W4320013936","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6640963894","https://openalex.org/W6695676441","https://openalex.org/W6731370813","https://openalex.org/W6749825310","https://openalex.org/W6754172774","https://openalex.org/W6755236810"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2064323827","https://openalex.org/W4309969736","https://openalex.org/W4394785709","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2470043383","https://openalex.org/W3034474024","https://openalex.org/W2770818364","https://openalex.org/W4317242571"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,104],"approach":[4],"to":[5,59,115,121],"the":[6,10,26,33,42,45,49,55,60,64,68,90,116,124,128],"joint":[7],"modeling":[8],"of":[9,44,81,97],"short-time":[11],"Fourier":[12],"transform":[13],"magnitude":[14,27,107],"and":[15,32,67,77,109,148],"phase":[16,34,46,61,111,125],"spectrograms":[17],"with":[18,143],"a":[19,29,36,106,110,133,144,149],"deep":[20],"generative":[21],"model.":[22],"We":[23],"assume":[24],"that":[25],"follows":[28,35],"Gaussian":[30],"distribution":[31,58],"von":[37,56],"Mises":[38,57],"distribution.":[39],"To":[40],"improve":[41],"consistency":[43],"values":[47],"in":[48],"time-frequency":[50],"domain,":[51],"we":[52,75,119],"also":[53,122],"apply":[54],"derivatives,":[62],"i.e.,":[63],"group":[65],"delay":[66],"instantaneous":[69],"frequency.":[70],"Based":[71],"on":[72,127],"these":[73],"assumptions,":[74],"explore":[76],"compare":[78],"several":[79],"combinations":[80],"loss":[82],"functions":[83],"for":[84,132],"training":[85],"our":[86,94,138],"models.":[87],"Built":[88],"upon":[89],"variational":[91],"autoencoder":[92],"framework,":[93],"model":[95],"consists":[96],"three":[98],"convolutional":[99],"neural":[100],"networks":[101],"acting":[102],"as":[103],"encoder,":[105],"decoder,":[108],"decoder.":[112],"In":[113],"addition":[114],"latent":[117],"variables,":[118],"propose":[120],"condition":[123],"estimation":[126],"estimated":[129],"magnitude.":[130],"Evaluated":[131],"time-domain":[134],"speech":[135,142],"reconstruction":[136],"task,":[137],"models":[139],"could":[140],"generate":[141],"high":[145,150],"perceptual":[146],"quality":[147],"intelligibility.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}