{"id":"https://openalex.org/W4406461897","doi":"https://doi.org/10.1109/slt61566.2024.10832188","title":"Stage-Wise and Prior-Aware Neural Speech Phase Prediction","display_name":"Stage-Wise and Prior-Aware Neural Speech Phase Prediction","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461897","doi":"https://doi.org/10.1109/slt61566.2024.10832188"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5115602455","display_name":"Fei Liu","orcid":"https://orcid.org/0000-0002-9814-4226"},"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":true,"raw_author_name":"Fei Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"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":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"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":"Ye-Xin Lu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310848","display_name":"Rui-Chen Zheng","orcid":null},"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":"Rui-Chen Zheng","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115602455"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23852576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"638","last_page":"644"},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.7229942083358765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5540338754653931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4402286112308502},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43314605951309204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3310088515281677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229942083358765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5540338754653931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4402286112308502},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43314605951309204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3310088515281677}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"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":32,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2152859600","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/W2899663614","https://openalex.org/W2902806197","https://openalex.org/W2951310434","https://openalex.org/W2962911378","https://openalex.org/W2964243274","https://openalex.org/W2989528444","https://openalex.org/W3016129867","https://openalex.org/W3092028330","https://openalex.org/W3096709315","https://openalex.org/W3104557543","https://openalex.org/W4205689591","https://openalex.org/W4224918667","https://openalex.org/W4372260247","https://openalex.org/W4386076493","https://openalex.org/W4394595435","https://openalex.org/W6727697161","https://openalex.org/W6755977528","https://openalex.org/W6758708508","https://openalex.org/W6780226713","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,35,53,81,98],"novel":[4],"Stage-wise":[5],"and":[6,74,135],"Prior-aware":[7],"Neural":[8],"Speech":[9],"Phase":[10],"Prediction":[11],"(SP-NSPP)":[12],"model,":[13],"which":[14],"predicts":[15],"the":[16,28,41,49,60,72,89,92,105,120,131],"phase":[17,38,56,82,117,125,133,142],"spectrum":[18,22,39,51,57,83],"from":[19,40],"input":[20],"amplitude":[21,42,50],"by":[23,78],"two-stage":[24],"neural":[25,114],"networks.":[26],"In":[27],"initial":[29],"prior-construction":[30],"stage,":[31],"we":[32,95],"preliminarily":[33],"predict":[34],"rough":[36],"prior":[37,61],"spectrum.":[43],"The":[44],"subsequent":[45],"refinement":[46,106],"stage":[47],"transforms":[48],"into":[52],"refined":[54,93],"high-quality":[55],"conditioned":[58],"on":[59],"phase.":[62],"Networks":[63],"in":[64,104,157],"both":[65],"stages":[66],"use":[67],"ConvNeXt":[68],"v2":[69],"blocks":[70],"as":[71],"backbone":[73],"adopt":[75],"adversarial":[76],"training":[77,137],"innovatively":[79],"introducing":[80,130],"discriminator":[84],"(PSD).":[85],"To":[86],"further":[87],"improve":[88],"continuity":[90],"of":[91,153],"phase,":[94],"also":[96],"incorporate":[97],"time-frequency":[99],"integrated":[100],"difference":[101],"(TFID)":[102],"loss":[103],"stage.":[107],"Experimental":[108],"results":[109],"confirm":[110],"that,":[111],"compared":[112],"to":[113,129,140],"network-based":[115],"no-prior":[116],"prediction":[118,126],"methods,":[119],"proposed":[121,146],"SP-NSPP":[122,147],"achieves":[123],"higher":[124,158],"accuracy,":[127],"thanks":[128],"coarse":[132],"priors":[134],"diverse":[136],"criteria.":[138],"Compared":[139],"iterative":[141],"estimation":[143],"algorithms,":[144],"our":[145],"does":[148],"not":[149],"require":[150],"multiple":[151],"rounds":[152],"staged":[154],"iterations,":[155],"resulting":[156],"generation":[159],"efficiency.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}