{"id":"https://openalex.org/W3197095449","doi":"https://doi.org/10.21437/interspeech.2021-2173","title":"Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition","display_name":"Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197095449","doi":"https://doi.org/10.21437/interspeech.2021-2173","mag":"3197095449"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5033917478","display_name":"Zhengxi Liu","orcid":"https://orcid.org/0000-0002-9345-8154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengxi Liu","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100341993"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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":0.9958999752998352,"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":0.9908000230789185,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806832790374756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6668528318405151},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5442531108856201},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4803786873817444},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44159895181655884},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4066440463066101},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.36364269256591797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32026755809783936},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.31537944078445435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09277191758155823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806832790374756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6668528318405151},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5442531108856201},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4803786873817444},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44159895181655884},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4066440463066101},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.36364269256591797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32026755809783936},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31537944078445435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09277191758155823},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2163202748","https://openalex.org/W2168103112","https://openalex.org/W2189422931","https://openalex.org/W2519091744","https://openalex.org/W2519994964","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3096702751","https://openalex.org/W3103104054","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1828907027","https://openalex.org/W1996547972","https://openalex.org/W1975359510","https://openalex.org/W2754746744","https://openalex.org/W2187141954","https://openalex.org/W2170815394","https://openalex.org/W4382560817","https://openalex.org/W1985168493","https://openalex.org/W2748661748"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2,23],"shown":[3,24],"that":[4],"neural":[5,21,58,112,167],"vocoders":[6,22,59],"based":[7,20,33,111,166],"on":[8,34,45],"generative":[9],"adversarial":[10],"network":[11],"(GAN)":[12],"can":[13,156],"generate":[14],"audios":[15],"with":[16,91,123,141,159,163],"high":[17],"quality.While":[18],"GAN":[19,110,165],"to":[25,69,187],"be":[26,157],"computationally":[27],"much":[28,160],"more":[29],"efficient":[30],"than":[31],"those":[32],"autoregressive":[35],"predictions,":[36],"the":[37,41,62,71,74,82,92,101,117,131,137,147,151,169],"real-time":[38],"generation":[39],"of":[40,55,73,77,85,94,103,134,146],"highest":[42],"quality":[43],"audio":[44,119,149,176],"CPU":[46],"is":[47,88],"still":[48],"a":[49,108,124],"very":[50],"challenging":[51],"task.One":[52],"major":[53],"computation":[54,102],"all":[56],"GAN-based":[57],"comes":[60],"from":[61,182],"stacked":[63],"upsampling":[64,86,104,152],"layers,":[65,105],"which":[66],"were":[67],"designed":[68,158],"match":[70],"length":[72,76],"waveform's":[75],"output":[78],"and":[79,127],"temporal":[80],"resolution.Meanwhile,":[81],"computational":[83,180],"complexity":[84,181],"networks":[87],"closely":[89],"correlated":[90],"numbers":[93],"samples":[95,120],"generated":[96],"for":[97],"each":[98,142],"window.To":[99],"reduce":[100],"we":[106],"propose":[107],"new":[109],"vocoder":[113],"called":[114],"Basis-MelGAN":[115,135,155,171],"where":[116],"raw":[118,148],"are":[121,136],"decomposed":[122],"learned":[125,143],"basis":[126,144],"their":[128],"associated":[129,140],"weights.As":[130],"prediction":[132],"targets":[133],"weight":[138],"values":[139],"instead":[145],"samples,":[150],"layers":[153],"in":[154],"simpler":[161],"networks.Compared":[162],"other":[164],"vocoders,":[168],"proposed":[170],"could":[172],"produce":[173],"comparable":[174],"high-quality":[175],"but":[177],"significantly":[178],"reduced":[179],"HiFi-GAN":[183],"V1's":[184],"17.74":[185],"GFLOPs":[186],"7.95":[188],"GFLOPs.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}