{"id":"https://openalex.org/W4372260247","doi":"https://doi.org/10.1109/icassp49357.2023.10096553","title":"Neural Speech Phase Prediction Based on Parallel Estimation Architecture and Anti-Wrapping Losses","display_name":"Neural Speech Phase Prediction Based on Parallel Estimation Architecture and Anti-Wrapping Losses","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260247","doi":"https://doi.org/10.1109/icassp49357.2023.10096553"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"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"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, 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","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"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"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.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":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7258636951446533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6542611718177795},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.6297163367271423},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6118839979171753},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5539483428001404},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5386146903038025},{"id":"https://openalex.org/keywords/instantaneous-phase","display_name":"Instantaneous phase","score":0.47498244047164917},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4327791631221771},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4286526143550873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3875468373298645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28069186210632324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23670727014541626},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13014909625053406}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7258636951446533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542611718177795},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.6297163367271423},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6118839979171753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5539483428001404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5386146903038025},{"id":"https://openalex.org/C137798554","wikidata":"https://www.wikidata.org/wiki/Q6038852","display_name":"Instantaneous phase","level":3,"score":0.47498244047164917},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4327791631221771},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4286526143550873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3875468373298645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28069186210632324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23670727014541626},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13014909625053406},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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":23,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2120847449","https://openalex.org/W2129142580","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/W2567070169","https://openalex.org/W2749881488","https://openalex.org/W2874689226","https://openalex.org/W2908510526","https://openalex.org/W2951310434","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2989528444","https://openalex.org/W3015213667","https://openalex.org/W3016129867","https://openalex.org/W3104557543","https://openalex.org/W6727697161","https://openalex.org/W6731370813","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W3181746755","https://openalex.org/W2521062615","https://openalex.org/W3016958897","https://openalex.org/W2782645198","https://openalex.org/W2704904180","https://openalex.org/W4283379348","https://openalex.org/W3094412894","https://openalex.org/W2735477435","https://openalex.org/W3045739591","https://openalex.org/W2807436399"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,25,28,33,50],"novel":[4],"speech":[5,133,152],"phase":[6,12,51,60,76,91,103,112,134],"prediction":[7,135],"model":[8,23,136],"which":[9],"predicts":[10],"wrapped":[11,102],"spectra":[13,17,61,70,104],"directly":[14],"from":[15,62],"amplitude":[16],"by":[18,90,108],"neural":[19,132,144],"networks.":[20],"The":[21,37],"proposed":[22,131],"is":[24,41],"cascade":[26],"of":[27,43,57,68,149],"residual":[29],"convolutional":[30,47],"network":[31],"and":[32,49,65,71,105,117,142,154],"parallel":[34,38,45],"estimation":[35,39],"architecture.":[36],"architecture":[40],"composed":[42],"two":[44],"linear":[46],"layers":[48],"calculation":[52],"formula,":[53],"imitating":[54],"the":[55,59,63,74,79,85,100,110,138],"process":[56],"calculating":[58],"real":[64],"imaginary":[66],"parts":[67],"complex":[69],"strictly":[72],"restricting":[73],"predicted":[75,101],"values":[77],"to":[78],"principal":[80],"value":[81],"interval.":[82],"To":[83],"avoid":[84],"error":[86,116,121],"expansion":[87],"issue":[88],"caused":[89],"wrapping,":[92],"we":[93],"design":[94],"anti-wrapping":[95,124],"training":[96],"losses":[97],"defined":[98],"between":[99],"natural":[106],"ones":[107],"activating":[109],"instantaneous":[111,118],"error,":[113],"group":[114],"delay":[115],"angular":[119],"frequency":[120],"using":[122],"an":[123],"function.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"our":[130],"outperforms":[137],"iterative":[139],"Griffin-Lim":[140],"algorithm":[141],"other":[143],"network-based":[145],"method,":[146],"in":[147],"terms":[148],"both":[150],"reconstructed":[151],"quality":[153],"generation":[155],"speed.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}