{"id":"https://openalex.org/W4416798833","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249404","title":"Neural Speech Separation with Parallel Amplitude and Phase Spectrum Estimation","display_name":"Neural Speech Separation with Parallel Amplitude and Phase Spectrum Estimation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798833","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249404"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":false,"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,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,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,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,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":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,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,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39337139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"642","last_page":"647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8924999833106995,"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":0.8924999833106995,"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":0.08160000294446945,"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/T10863","display_name":"Voice and Speech Disorders","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.7267000079154968},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.49790000915527344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47780001163482666},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4562999904155731},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.4228000044822693},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4108000099658966},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38830000162124634}],"concepts":[{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.7267000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5253000259399414},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4952999949455261},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C57747864","wikidata":"https://www.wikidata.org/wiki/Q7180948","display_name":"Phase distortion","level":3,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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/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}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1981755271","https://openalex.org/W1991139021","https://openalex.org/W2062470211","https://openalex.org/W2113131123","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2476548250","https://openalex.org/W2561557072","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2972460025","https://openalex.org/W2981436548","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3015834770","https://openalex.org/W3042857426","https://openalex.org/W3085139254","https://openalex.org/W3096893582","https://openalex.org/W3160903688","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W4224936432","https://openalex.org/W4372260247","https://openalex.org/W4385823047","https://openalex.org/W4410314146"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"APSS,":[3],"a":[4,63,75],"novel":[5],"neural":[6],"speech":[7,20,51,121],"separation":[8,21,131],"model":[9],"with":[10,78],"parallel":[11,89],"amplitude":[12,44,56,90],"and":[13,36,45,57,84,91,133,141,152],"phase":[14,31,46,58,92],"spectrum":[15,32],"estimation.":[16],"Unlike":[17],"most":[18],"existing":[19],"methods,":[22],"the":[23,30,43,49,54,94,97,104,119],"APSS":[24,40,95,127,138],"distinguishes":[25],"itself":[26],"by":[27,62,74],"explicitly":[28],"estimating":[29],"for":[33,100],"more":[34],"complete":[35],"accurate":[37],"separation.":[38],"Specifically,":[39],"first":[41],"extracts":[42],"spectra":[47,59,99],"from":[48,103],"mixed":[50],"signal.":[52],"Subsequently,":[53],"extracted":[55],"are":[60,70,108],"fused":[61],"feature":[64],"combiner":[65],"into":[66],"joint":[67],"representations,":[68],"which":[69,107],"then":[71,109],"further":[72],"processed":[73],"deep":[76],"processor":[77],"time-frequency":[79,135],"Transformers":[80],"to":[81,117],"capture":[82],"temporal":[83],"spectral":[85],"dependencies.":[86],"Finally,":[87],"leveraging":[88],"separators,":[93],"estimates":[96],"respective":[98],"each":[101],"speaker":[102],"resulting":[105],"features,":[106],"combined":[110],"via":[111],"inverse":[112],"short-time":[113],"Fourier":[114],"transform":[115],"(iSTFT)":[116],"reconstruct":[118],"separated":[120],"signals.":[122],"Experimental":[123],"results":[124,143],"indicate":[125],"that":[126],"surpasses":[128],"both":[129],"time-domain":[130],"methods":[132],"implicit-phase-estimation-based":[134],"approaches.":[136],"Also,":[137],"achieves":[139],"stable":[140],"competitive":[142],"on":[144],"multiple":[145],"datasets,":[146],"highlighting":[147],"its":[148],"strong":[149],"generalization":[150],"capability":[151],"practical":[153],"applicability.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}