{"id":"https://openalex.org/W4385688722","doi":"https://doi.org/10.1109/ssp53291.2023.10207969","title":"Exploring the Potential of VAE Decoders for Enhanced Speech Re-Synthesis","display_name":"Exploring the Potential of VAE Decoders for Enhanced Speech Re-Synthesis","publication_year":2023,"publication_date":"2023-07-02","ids":{"openalex":"https://openalex.org/W4385688722","doi":"https://doi.org/10.1109/ssp53291.2023.10207969"},"language":"en","primary_location":{"id":"doi:10.1109/ssp53291.2023.10207969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssp53291.2023.10207969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","raw_type":"proceedings-article"},"type":"article","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/A5067277293","display_name":"Omead Pooladzandi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Omead Pooladzandi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639669","display_name":"Xi-Lin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XiLin Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013420855","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0001-9328-1611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029532311","display_name":"Lalin Theverapperuma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lalin Theverapperuma","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067277293"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2068,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42891102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1910 10942","issue":null,"first_page":"359","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921886444091797},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7769984006881714},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6399731636047363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6027705669403076},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.518890917301178},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4747636318206787},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4401080310344696},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4129485487937927},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41079390048980713},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.34711211919784546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3393581509590149},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13387733697891235},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1210218071937561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921886444091797},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7769984006881714},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6399731636047363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6027705669403076},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.518890917301178},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4747636318206787},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4401080310344696},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4129485487937927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41079390048980713},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.34711211919784546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393581509590149},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13387733697891235},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1210218071937561},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssp53291.2023.10207969","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssp53291.2023.10207969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1560013842","https://openalex.org/W1975710323","https://openalex.org/W2039844283","https://openalex.org/W2217490359","https://openalex.org/W2584505851","https://openalex.org/W2798933118","https://openalex.org/W2883083347","https://openalex.org/W2999890176","https://openalex.org/W3005621653","https://openalex.org/W3095797429","https://openalex.org/W3185637724","https://openalex.org/W3201698955","https://openalex.org/W4289490877","https://openalex.org/W4308672465","https://openalex.org/W6757476456","https://openalex.org/W6769302077","https://openalex.org/W6773240189"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,66],"study":[4],"different":[5],"Variational":[6],"Autoencoders":[7],"(VAEs)":[8],"decoder":[9,35,49,85,95,104],"distributions":[10],"in":[11,77,126],"the":[12,33,69,83,92,119,127,133,136,140],"audio":[13],"setting":[14],"to":[15,18,46,63],"see":[16,64],"how":[17],"improve":[19,68],"magnitude":[20,59,88],"and":[21,41,60,90,122,145],"phase":[22,61,99],"reconstruction":[23,89],"on":[24,32],"speech":[25,78,143],"resynthesis":[26,144],"tasks.":[27],"We":[28,53],"first":[29],"provide":[30],"background":[31],"existing":[34],"distributions,":[36],"such":[37],"as":[38],"Complex":[39],"Gaussian":[40],"Laplace,":[42],"which":[43],"are":[44],"equivalent":[45],"a":[47,109,115],"Gamma":[48,84,103],"under":[50],"certain":[51],"conditions.":[52],"then":[54],"consider":[55],"separately":[56],"modeling":[57],"speech\u2019s":[58],"information":[62],"if":[65],"can":[67,96],"quality":[70,141],"of":[71,112,135,142,148],"either":[72],"component,":[73],"yielding":[74],"an":[75,123],"improvement":[76,117],"resynthesis.":[79],"Extensive":[80],"experiments":[81],"show":[82],"significantly":[86],"improves":[87],"that":[91],"von":[93],"Mises":[94],"weakly":[97],"learn":[98],"information.":[100],"The":[101],"novel":[102,137],"outperforms":[105],"previous":[106],"approaches,":[107],"achieving":[108],"near-perfect":[110],"PESQ":[111],"4.4,":[113],"representing":[114],"42%":[116],"upon":[118],"state-of-the-art":[120],"IS-VAE":[121],"86%":[124],"decrease":[125],"FAD":[128],"metric.":[129],"Our":[130],"results":[131],"demonstrate":[132],"effectiveness":[134],"approach,":[138],"improving":[139],"compression":[146],"capacity":[147],"VAEs.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}