{"id":"https://openalex.org/W4387350832","doi":"https://doi.org/10.1109/taslp.2023.3321191","title":"A Fast High-Fidelity Source-Filter Vocoder With Lightweight Neural Modules","display_name":"A Fast High-Fidelity Source-Filter Vocoder With Lightweight Neural Modules","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387350832","doi":"https://doi.org/10.1109/taslp.2023.3321191"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3321191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3321191","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5006425914","display_name":"Runxuan Yang","orcid":"https://orcid.org/0009-0004-2526-1909"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runxuan Yang","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2526-1909","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769130","display_name":"Yuyang Peng","orcid":"https://orcid.org/0009-0005-1955-2635"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Peng","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1955-2635","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004579631","display_name":"Xiaolin Hu","orcid":"https://orcid.org/0000-0002-4907-7354"},"institutions":[{"id":"https://openalex.org/I4210115644","display_name":"Chinese Institute for Brain Research","ror":"https://ror.org/029819q61","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210115644"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","Chinese Institute for Brain Research (CIBR), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4907-7354","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, State Key Laboratory of Intelligent Technology and Systems, Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute for AI, THBI, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Chinese Institute for Brain Research (CIBR), Beijing, China","institution_ids":["https://openalex.org/I4210115644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0438,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77332048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3362","last_page":"3373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8579440712928772},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5093492269515991},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4935644865036011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4840644896030426},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4622513949871063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31073710322380066},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21939289569854736},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12952783703804016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579440712928772},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5093492269515991},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4935644865036011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4840644896030426},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4622513949871063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31073710322380066},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21939289569854736},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12952783703804016},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3321191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3321191","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G4160143202","display_name":"\u7c7b\u8111\u795e\u7ecf\u7f51\u7edc\u5efa\u6a21\u3001\u5b66\u4e60\u4e0e\u5e94\u7528","funder_award_id":"61836014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379697419","display_name":null,"funder_award_id":"62061136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1563089615","https://openalex.org/W1665214252","https://openalex.org/W2012086895","https://openalex.org/W2064948657","https://openalex.org/W2074783531","https://openalex.org/W2097645910","https://openalex.org/W2120847449","https://openalex.org/W2131062138","https://openalex.org/W2151409182","https://openalex.org/W2152205330","https://openalex.org/W2161632835","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2531409750","https://openalex.org/W2584032004","https://openalex.org/W2745319348","https://openalex.org/W2747070883","https://openalex.org/W2890983311","https://openalex.org/W2962866891","https://openalex.org/W2962898107","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2970006822","https://openalex.org/W2972333964","https://openalex.org/W2990440871","https://openalex.org/W3000389243","https://openalex.org/W3011176162","https://openalex.org/W3015338123","https://openalex.org/W3041738652","https://openalex.org/W3045000780","https://openalex.org/W3092028330","https://openalex.org/W3095448311","https://openalex.org/W3096429957","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3130168980","https://openalex.org/W3197273793","https://openalex.org/W3197385343","https://openalex.org/W4221152438","https://openalex.org/W4225566824","https://openalex.org/W4245284779","https://openalex.org/W4285345683","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4372262501","https://openalex.org/W4372262701","https://openalex.org/W6633684334","https://openalex.org/W6637242042","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6767111847","https://openalex.org/W6771763809","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W4214484837","https://openalex.org/W2770826937","https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2375008505","https://openalex.org/W1982750869","https://openalex.org/W3096216989","https://openalex.org/W2085756966"],"abstract_inverted_index":{"The":[0],"quality":[1,158],"of":[2,21,93,101],"raw":[3],"audio":[4,13,37,157],"waveform":[5],"generated":[6],"by":[7,27,89],"a":[8,67,77,139,166],"vocoder":[9],"could":[10],"affect":[11],"various":[12],"generative":[14],"tasks.":[15],"In":[16],"recent":[17],"years,":[18],"the":[19,31,82,102,135],"dominance":[20],"source-filter":[22,70,104,183],"vocoders":[23,29,41,105,164],"was":[24],"greatly":[25],"challenged":[26],"neural":[28,40,129,163],"as":[30,49,51,180],"latter":[32],"presents":[33],"far":[34],"superior":[35],"synthesized":[36,156],"quality.":[38],"Meanwhile,":[39],"introduced":[42],"unprecedented":[43],"limitations":[44],"including":[45],"low":[46],"runtime":[47],"efficiency":[48],"well":[50],"unstable":[52],"pitch":[53,178],"especially":[54],"in":[55,69,74,97,181],"those":[56],"without":[57],"explicit":[58],"periodic":[59],"excitation":[60],"input,":[61],"while":[62,171],"these":[63],"have":[64],"never":[65],"been":[66],"problem":[68],"vocoders.":[71,184],"We":[72,87,132],"present":[73,154],"this":[75],"paper":[76],"novel":[78],"approach":[79],"that":[80,115,151],"takes":[81],"best":[83],"from":[84],"both":[85],"parties.":[86],"start":[88],"an":[90],"in-depth":[91],"examination":[92],"every":[94],"building":[95,143],"block":[96],"WORLD":[98],"\u2013":[99],"one":[100],"best-performing":[103],"based":[106],"on":[107],"plain":[108],"signal":[109],"processing":[110],"algorithms,":[111],"looking":[112],"for":[113,138],"ones":[114],"do":[116],"not":[117],"work":[118],"well,":[119],"and":[120,127,147],"we":[121],"replace":[122],"them":[123],"with":[124],"small,":[125],"lightweight":[126],"task-specific":[128],"network":[130],"models.":[131],"also":[133],"rearranged":[134],"vocoding":[136],"pipeline":[137],"smoother":[140],"collaboration":[141],"between":[142],"blocks.":[144],"Our":[145],"objective":[146],"subjective":[148],"evaluations":[149],"demonstrate":[150],"our":[152],"methods":[153],"competitive":[155],"even":[159],"when":[160],"compared":[161],"against":[162],"at":[165],"much":[167],"lower":[168],"computational":[169],"cost,":[170],"keeping":[172],"spectral":[173],"envelope":[174],"acoustic":[175],"feature,":[176],"high":[177],"accuracy":[179],"conventional":[182]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}