{"id":"https://openalex.org/W4377000449","doi":"https://doi.org/10.1109/taslp.2023.3277276","title":"APNet: An All-Frame-Level Neural Vocoder Incorporating Direct Prediction of Amplitude and Phase Spectra","display_name":"APNet: An All-Frame-Level Neural Vocoder Incorporating Direct Prediction of Amplitude and Phase Spectra","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4377000449","doi":"https://doi.org/10.1109/taslp.2023.3277276"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3277276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277276","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/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.6966,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91435705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2145","last_page":"2157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9926000237464905,"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":0.7197548151016235},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6263498067855835},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6110225319862366},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5977546572685242},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5776503086090088},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5675869584083557},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5249545574188232},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.48086315393447876},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4696499705314636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45925232768058777},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4352940320968628},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3576483726501465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19547390937805176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.193087637424469},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15390446782112122},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.13747569918632507},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10941216349601746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197548151016235},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6263498067855835},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6110225319862366},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5977546572685242},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5776503086090088},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5675869584083557},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5249545574188232},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.48086315393447876},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4696499705314636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45925232768058777},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4352940320968628},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3576483726501465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19547390937805176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.193087637424469},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15390446782112122},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.13747569918632507},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10941216349601746},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3277276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3277276","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":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1080972157","display_name":null,"funder_award_id":"WK2100000033","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8663906801","display_name":"\u9762\u5411\u8bed\u97f3\u5408\u6210\u7684\u795e\u7ecf\u7f51\u7edc\u58f0\u7801\u5668\u7814\u7a76","funder_award_id":"61871358","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2115098197","https://openalex.org/W2129142580","https://openalex.org/W2292984643","https://openalex.org/W2294797155","https://openalex.org/W2471520273","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2803595463","https://openalex.org/W2803714261","https://openalex.org/W2889329491","https://openalex.org/W2903739847","https://openalex.org/W2929299742","https://openalex.org/W2940417587","https://openalex.org/W2951310434","https://openalex.org/W2954386831","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2975414524","https://openalex.org/W3015338123","https://openalex.org/W3095749709","https://openalex.org/W3096080837","https://openalex.org/W3104557543","https://openalex.org/W3144035034","https://openalex.org/W3145039504","https://openalex.org/W4221152438","https://openalex.org/W4221155904","https://openalex.org/W4285121050","https://openalex.org/W4372341094","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6755257315","https://openalex.org/W6757817989","https://openalex.org/W6767111847","https://openalex.org/W6771024825","https://openalex.org/W6783867762","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,35,43,60,87,177],"novel":[4],"neural":[5],"vocoder":[6,25,165,201],"named":[7],"APNet":[8,24,164,200],"which":[9,47],"reconstructs":[10],"speech":[11,107,187,196,239],"waveforms":[12,108],"from":[13,53],"acoustic":[14,54,65],"features":[15,66],"by":[16,109],"predicting":[17],"amplitude":[18,30,51,142],"and":[19,34,83,101,120,132,135,153,228],"phase":[20,36,88,94,146,220,226],"spectra":[21,52],"directly.":[22],"The":[23,40,56,194],"is":[26,42,189,202,223],"composed":[27],"of":[28,73,99,117,198,207],"an":[29,167],"spectrum":[31,37],"predictor":[32,38],"(ASP)":[33],"(PSP).":[39],"ASP":[41,100,119,131],"residual":[44,61],"convolution":[45,62,80],"network":[46,63,75],"predicts":[48],"frame-level":[49,93],"log":[50],"features.":[55],"PSP":[57,102,121,133],"also":[58,203,214],"adopts":[59],"using":[64],"as":[67],"input,":[68],"then":[69],"passes":[70],"the":[71,97,118,125,130,181,199,217,229,237],"output":[72],"this":[74],"through":[76],"two":[77],"parallel":[78,219],"linear":[79],"layers":[81],"respectively,":[82],"finally":[84],"integrates":[85],"into":[86],"calculation":[89],"formula":[90],"to":[91,105,180,191,225],"estimate":[92],"spectra.":[95],"Finally,":[96],"outputs":[98],"are":[103,122,233],"combined":[104],"reconstruct":[106],"inverse":[110],"short-time":[111,149],"Fourier":[112],"transform":[113],"(ISTFT).":[114],"All":[115],"operations":[116],"performed":[123],"at":[124],"frame":[126],"level.":[127],"We":[128],"train":[129],"jointly":[134],"define":[136],"multilevel":[137],"loss":[138,231],"functions":[139,232],"based":[140],"on":[141,176],"mean":[143],"square":[144],"error,":[145,148],"anti-wrapping":[147],"spectral":[150],"inconsistency":[151],"error":[152],"time":[154],"domain":[155],"reconstruction":[156],"error.":[157],"Experimental":[158],"results":[159],"show":[160],"that":[161,206,216],"our":[162],"proposed":[163,218,230],"achieves":[166],"approximately":[168],"8x":[169],"faster":[170],"inference":[171],"speed":[172],"than":[173,205],"HiFi-GAN":[174,192],"v1":[175],"CPU":[178],"due":[179],"all-frame-level":[182],"operations,":[183],"while":[184],"its":[185],"synthesized":[186,195,238],"quality":[188,197],"comparable":[190],"v1.":[193],"better":[204],"several":[208],"equally":[209],"efficient":[210],"models.":[211],"Ablation":[212],"experiments":[213],"confirm":[215],"estimation":[221],"architecture":[222],"essential":[224],"modeling":[227],"helpful":[234],"for":[235],"improving":[236],"quality.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}