{"id":"https://openalex.org/W4392902735","doi":"https://doi.org/10.1109/icassp48485.2024.10448279","title":"Phase Reconstruction in Single Channel Speech Enhancement Based on Phase Gradients and Estimated Clean-Speech Amplitudes","display_name":"Phase Reconstruction in Single Channel Speech Enhancement Based on Phase Gradients and Estimated Clean-Speech Amplitudes","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902735","doi":"https://doi.org/10.1109/icassp48485.2024.10448279"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01HW539RK24J7CMH02CWC6FHQE/file/01HW53BRXYAFVQ4VMZJVHMV4JX.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007667052","display_name":"Yanjue Song","orcid":"https://orcid.org/0000-0002-9684-6611"},"institutions":[{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Yanjue Song","raw_affiliation_strings":["Ghent University - Imec,IDLab, Department of Electronics and Information Systems,Belgium","IDLab, Department of Electronics and Information Systems, Ghent University - Imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab, Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - Imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - Imec,IDLab, Department of Electronics and Information Systems,Belgium","IDLab, Department of Electronics and Information Systems, Ghent University - Imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - Imec,IDLab, Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - Imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007667052"],"corresponding_institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65042566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1461","last_page":"1465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7807284593582153},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7529273629188538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6798495054244995},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.6658214926719666},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.6023489832878113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5257883071899414},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.28503191471099854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2295839786529541},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18297576904296875},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13546323776245117},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13510799407958984}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7807284593582153},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7529273629188538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798495054244995},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.6658214926719666},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.6023489832878113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5257883071899414},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.28503191471099854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2295839786529541},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18297576904296875},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13546323776245117},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13510799407958984},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01HW539RK24J7CMH02CWC6FHQE","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HW539RK24J7CMH02CWC6FHQE","pdf_url":"https://biblio.ugent.be/publication/01HW539RK24J7CMH02CWC6FHQE/file/01HW53BRXYAFVQ4VMZJVHMV4JX.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798350344868","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01HW539RK24J7CMH02CWC6FHQE","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HW539RK24J7CMH02CWC6FHQE","pdf_url":"https://biblio.ugent.be/publication/01HW539RK24J7CMH02CWC6FHQE/file/01HW53BRXYAFVQ4VMZJVHMV4JX.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798350344868","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392902735.pdf","grobid_xml":"https://content.openalex.org/works/W4392902735.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1529537891","https://openalex.org/W1974542390","https://openalex.org/W1995144245","https://openalex.org/W2041498927","https://openalex.org/W2067295501","https://openalex.org/W2070126272","https://openalex.org/W2291877678","https://openalex.org/W2516594951","https://openalex.org/W2734774145","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3097906045","https://openalex.org/W3103301587","https://openalex.org/W3147539069","https://openalex.org/W3160129476","https://openalex.org/W3161480375","https://openalex.org/W3161748343","https://openalex.org/W3163464523","https://openalex.org/W4214498238","https://openalex.org/W4285119904","https://openalex.org/W4309210956"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W4385769873","https://openalex.org/W4281634296","https://openalex.org/W2055945594","https://openalex.org/W3003855539","https://openalex.org/W2088275829","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Phase":[0],"gradients":[1,28],"can":[2],"help":[3],"enforce":[4],"phase":[5,27,43,54,66,72,92,110,125,161,170],"consistency":[6],"across":[7],"time":[8],"and":[9,150],"frequency,":[10],"further":[11,140],"improving":[12],"the":[13,26,30,70,76,87,91,97,101,113,135,137,142,153,185,188],"output":[14,114],"of":[15,34,75,89,100,115,187],"speech":[16,56,118,175,199],"enhancement":[17,57,111,119,162],"approaches.":[18],"Recently,":[19],"neural":[20],"networks":[21,95],"were":[22,38],"used":[23,40],"to":[24,41,44,112,134,165],"estimate":[25,67],"from":[29],"short-term":[31],"amplitude":[32,98],"spectra":[33,99,176],"clean":[35],"speech.":[36],"These":[37],"then":[39],"synthesise":[42],"obtain":[45],"a":[46,64,116,195],"plausible":[47],"time-domain":[48],"signal.":[49,104],"However,":[50],"using":[51],"purely":[52],"synthetic":[53,71],"in":[55,152],"yields":[58],"unnatural-sounding":[59],"output.":[60,82],"Therefore":[61],"we":[62,84,106],"derive":[63],"closed-form":[65],"that":[68,74],"combines":[69],"with":[73],"enhanced":[77],"speech,":[78],"yielding":[79],"more":[80],"natural":[81],"Secondly,":[83],"empirically":[85],"evaluate":[86],"benefit":[88],"(re-)training":[90],"gradient":[93,171],"estimation":[94],"on":[96,148,156,173],"estimated":[102,174],"clean-speech":[103],"Lastly":[105],"apply":[107],"our":[108],"proposed":[109,138],"phase-aware":[117,189],"DNN,":[120],"verifying":[121],"if":[122],"an":[123],"independent":[124],"estimator":[126],"brings":[127],"additional":[128],"advantage.":[129],"Results":[130],"show":[131],"that,":[132],"compared":[133],"baseline,":[136],"approach":[139],"improves":[141,184],"DNSMOS":[143],"scores":[144],"by":[145],"\u2248":[146],"0.1":[147],"average,":[149],"significantly":[151],"first":[154],"quartile":[155],"broadband,":[157],"quasi-stationary":[158],"noises,":[159],"where":[160],"is":[163,177],"expected":[164],"have":[166],"maximum":[167],"benefit.":[168],"Training":[169],"estimators":[172],"additionally":[178],"beneficial":[179],"here.":[180],"Our":[181],"method":[182],"even":[183],"performance":[186],"approach,":[190],"indicating":[191],"its":[192],"feasibility":[193],"as":[194],"generic":[196],"post-processor":[197],"for":[198],"enhancement.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}