{"id":"https://openalex.org/W4394595435","doi":"https://doi.org/10.1109/taslp.2024.3385285","title":"Low-Latency Neural Speech Phase Prediction Based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks","display_name":"Low-Latency Neural Speech Phase Prediction Based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394595435","doi":"https://doi.org/10.1109/taslp.2024.3385285"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3385285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385285","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":1.3892,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83113685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"2283","last_page":"2296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.6595678925514221},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.645793616771698},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6383770108222961},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5431084632873535},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5180819034576416},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5072319507598877},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4352740943431854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2888340950012207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10470607876777649},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0926947295665741},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06349176168441772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6595678925514221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.645793616771698},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6383770108222961},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5431084632873535},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5180819034576416},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5072319507598877},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4352740943431854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2888340950012207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10470607876777649},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0926947295665741},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06349176168441772},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3385285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3385285","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":[],"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/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G3513075617","display_name":null,"funder_award_id":"23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","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/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W585975565","https://openalex.org/W1972822190","https://openalex.org/W2007593159","https://openalex.org/W2044893557","https://openalex.org/W2101769813","https://openalex.org/W2108078415","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2152859600","https://openalex.org/W2156122508","https://openalex.org/W2166406271","https://openalex.org/W2292984643","https://openalex.org/W2399742709","https://openalex.org/W2400830530","https://openalex.org/W2405774341","https://openalex.org/W2518315489","https://openalex.org/W2527729766","https://openalex.org/W2749881488","https://openalex.org/W2807065297","https://openalex.org/W2874689226","https://openalex.org/W2902806197","https://openalex.org/W2951310434","https://openalex.org/W2962911378","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964328256","https://openalex.org/W2989528444","https://openalex.org/W3015213667","https://openalex.org/W3016129867","https://openalex.org/W3096709315","https://openalex.org/W3104557543","https://openalex.org/W3161748343","https://openalex.org/W4224918667","https://openalex.org/W4285121050","https://openalex.org/W4372260247","https://openalex.org/W4377000449","https://openalex.org/W4385807442","https://openalex.org/W6727697161","https://openalex.org/W6731370813","https://openalex.org/W6757817989","https://openalex.org/W6758708508","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2576994247","https://openalex.org/W2608353378","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"This":[0,48],"paper":[1],"presents":[2],"a":[3,23,26,31,40,58],"novel":[4],"neural":[5,180,192],"speech":[6,171,181],"phase":[7,13,46,59,68,84,99,111,120,155,182,188,194,200],"prediction":[8,156,183,195,201],"model":[9,21,184,214],"which":[10],"predicts":[11],"wrapped":[12,45,110],"spectra":[14,69,78,112],"directly":[15],"from":[16,70],"amplitude":[17],"spectra.":[18],"The":[19,35],"proposed":[20,179,213],"is":[22,39],"cascade":[24],"of":[25,51,65,76,199,224],"residual":[27],"convolutional":[28,55],"network":[29],"and":[30,57,73,79,113,125,148,161,169,191,204],"parallel":[32,36,53],"estimation":[33,37,189],"architecture.":[34],"architecture":[38,49],"core":[41],"module":[42],"for":[43],"direct":[44],"prediction.":[47],"consists":[50],"two":[52],"linear":[54],"layers":[56],"calculation":[60],"formula,":[61],"imitating":[62],"the":[63,67,71,82,87,93,108,118,138,186,222],"process":[64],"calculating":[66],"real":[72],"imaginary":[74],"parts":[75],"complex":[77],"strictly":[80],"restricting":[81],"predicted":[83,109],"values":[85],"to":[86],"principal":[88],"value":[89],"interval.":[90],"To":[91],"avoid":[92],"error":[94,124,129],"expansion":[95],"issue":[96],"caused":[97],"by":[98,116,157],"wrapping,":[100],"we":[101],"design":[102],"anti-wrapping":[103,132,139],"training":[104,164],"losses":[105],"defined":[106],"between":[107],"natural":[114],"ones":[115],"activating":[117],"instantaneous":[119,126],"error,":[121],"group":[122],"delay":[123],"angular":[127],"frequency":[128],"using":[130],"an":[131],"function.":[133],"We":[134,150],"mathematically":[135],"demonstrate":[136],"that":[137,177],"function":[140],"should":[141],"possess":[142],"three":[143],"properties,":[144],"namely":[145],"parity,":[146],"periodicity":[147],"monotonicity.":[149],"also":[151,215],"achieve":[152],"low-latency":[153],"streamable":[154],"combining":[158],"causal":[159],"convolutions":[160],"knowledge":[162],"distillation":[163],"strategies.":[165],"For":[166],"both":[167],"analysis-synthesis":[168],"specific":[170],"generation":[172],"tasks,":[173],"experimental":[174],"results":[175],"show":[176],"our":[178,212],"outperforms":[185],"iterative":[187],"algorithms":[190],"network-based":[193],"methods":[196],"in":[197],"terms":[198],"precision,":[202],"efficiency":[203,218],"robustness.":[205],"Compared":[206],"with":[207],"HiFi-GAN-based":[208],"waveform":[209],"reconstruction":[210],"method,":[211],"shows":[216],"outstanding":[217],"advantages":[219],"while":[220],"ensuring":[221],"quality":[223],"synthesized":[225],"speech.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}