{"id":"https://openalex.org/W4375868823","doi":"https://doi.org/10.1109/icassp49357.2023.10096007","title":"Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity","display_name":"Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868823","doi":"https://doi.org/10.1109/icassp49357.2023.10096007"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110745444","display_name":"Ahmed Mustafa","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Mustafa","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042244085","display_name":"Jan B\u00fcthe","orcid":"https://orcid.org/0000-0001-5872-4325"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan B\u00fcthe","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA","University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019618009","display_name":"Mike Goodwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Goodwin","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0873,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74730737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9952999949455261,"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":0.8763270378112793},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5445544719696045},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5410096049308777},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5072543025016785},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4595910310745239},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4522266685962677},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4497237503528595},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34763574600219727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3243459463119507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2892816662788391},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1081521213054657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763270378112793},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5445544719696045},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5410096049308777},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5072543025016785},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4595910310745239},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4522266685962677},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4497237503528595},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34763574600219727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3243459463119507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2892816662788391},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1081521213054657},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":39,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2115098197","https://openalex.org/W2165291881","https://openalex.org/W2284050935","https://openalex.org/W2403891086","https://openalex.org/W2519091744","https://openalex.org/W2750167318","https://openalex.org/W2895654193","https://openalex.org/W2908510526","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3092791109","https://openalex.org/W3095459301","https://openalex.org/W3096702751","https://openalex.org/W3129651364","https://openalex.org/W3161236344","https://openalex.org/W3174758275","https://openalex.org/W3188073270","https://openalex.org/W3197095449","https://openalex.org/W3197273793","https://openalex.org/W3198020407","https://openalex.org/W3215615641","https://openalex.org/W4200483526","https://openalex.org/W4224920322","https://openalex.org/W4225566824","https://openalex.org/W4284972581","https://openalex.org/W4297841815","https://openalex.org/W4298580827","https://openalex.org/W6695676441","https://openalex.org/W6731370813","https://openalex.org/W6767111847","https://openalex.org/W6777664437","https://openalex.org/W6777781272","https://openalex.org/W6778625279","https://openalex.org/W6778672582","https://openalex.org/W6779192484"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W4224939635","https://openalex.org/W4292794827"],"abstract_inverted_index":{"GAN":[0,39,62,130],"vocoders":[1,40,63,117,131],"are":[2],"currently":[3],"one":[4],"of":[5,18,23,87,126],"the":[6,75,88],"state-of-the-art":[7],"methods":[8],"for":[9,61],"building":[10],"high-quality":[11],"neural":[12],"waveform":[13],"generative":[14],"models.":[15],"However,":[16],"most":[17],"their":[19],"architectures":[20],"require":[21],"dozens":[22],"billion":[24],"floating-point":[25],"operations":[26],"per":[27],"second":[28],"(GFLOPS)":[29],"to":[30,43,72],"generate":[31,74],"speech":[32],"waveforms":[33],"in":[34,79,84],"samplewise":[35],"manner.":[36,81],"This":[37,82,128],"makes":[38,129],"still":[41],"challenging":[42],"run":[44],"on":[45,67,96,134],"normal":[46],"CPUs":[47],"without":[48],"accelerators":[49],"or":[50],"parallel":[51],"computers.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"propose":[57],"a":[58,122],"new":[59],"architecture":[60],"that":[64,105],"mainly":[65],"depends":[66],"recurrent":[68],"and":[69,91,99,136],"fully-connected":[70],"networks":[71],"directly":[73],"time":[76],"domain":[77],"signal":[78],"framewise":[80],"results":[83,103],"considerable":[85],"reduction":[86],"computational":[89],"cost":[90],"enables":[92],"very":[93,123],"fast":[94],"generation":[95],"both":[97],"GPUs":[98],"low-complexity":[100],"CPUs.":[101],"Experimental":[102],"show":[104],"our":[106],"Framewise":[107],"WaveGAN":[108],"vocoder":[109],"achieves":[110],"significantly":[111],"higher":[112],"quality":[113],"than":[114],"auto-regressive":[115],"maximum-likelihood":[116],"such":[118],"as":[119],"LPCNet":[120],"at":[121],"low":[124],"complexity":[125],"1.2GFLOPS.":[127],"more":[132],"practical":[133],"edge":[135],"low-power":[137],"devices.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}