{"id":"https://openalex.org/W4408353530","doi":"https://doi.org/10.1109/icassp49660.2025.10887812","title":"An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement","display_name":"An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353530","doi":"https://doi.org/10.1109/icassp49660.2025.10887812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5058318424","display_name":"Pin-Jui Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pin-Jui Ku","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110979141","display_name":"Chun-Wei Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Wei Ho","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000242115","display_name":"Hao Yen","orcid":"https://orcid.org/0000-0001-8897-4368"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Yen","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058318424"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.6525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78628261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"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":0.996999979019165,"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":0.996999979019165,"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":0.977400004863739,"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/T11946","display_name":"Antenna Design and Optimization","score":0.9577999711036682,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6266792416572571},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5991867184638977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.555311381816864},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5189689993858337},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44539642333984375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41934582591056824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20862224698066711},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12394493818283081},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07256081700325012}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6266792416572571},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5991867184638977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555311381816864},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5189689993858337},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44539642333984375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41934582591056824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20862224698066711},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12394493818283081},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07256081700325012},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/679551","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/679551","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1536373746","https://openalex.org/W1552314771","https://openalex.org/W1920741591","https://openalex.org/W1976489750","https://openalex.org/W2011853193","https://openalex.org/W2013419672","https://openalex.org/W2040768220","https://openalex.org/W2041498927","https://openalex.org/W2044893557","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2095072097","https://openalex.org/W2101304342","https://openalex.org/W2120847449","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2149535104","https://openalex.org/W2345067732","https://openalex.org/W2401387233","https://openalex.org/W2516001803","https://openalex.org/W2696383692","https://openalex.org/W2874689226","https://openalex.org/W2963189033","https://openalex.org/W2963317762","https://openalex.org/W2991015288","https://openalex.org/W2998161426","https://openalex.org/W3015213667","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3120607380","https://openalex.org/W3161748343","https://openalex.org/W3201698955","https://openalex.org/W4221144097","https://openalex.org/W4372260247","https://openalex.org/W4375869120","https://openalex.org/W4384080510","https://openalex.org/W4385756463","https://openalex.org/W4385807442","https://openalex.org/W4385822478","https://openalex.org/W4392902873","https://openalex.org/W4406461266","https://openalex.org/W6744762798","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W1603736412","https://openalex.org/W4214692512","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W2373767407","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,125],"propose":[4],"a":[5,36,49,61,68,81,114],"novel":[6],"consistency-preserving":[7],"loss":[8,59,109],"function":[9],"for":[10],"recovering":[11],"the":[12,16,33,57,78,88,92,135,151,155,166],"phase":[13,19,34],"information":[14],"in":[15],"context":[17],"of":[18,52,63,80,90,106],"reconstruction":[20],"(PR)":[21],"and":[22,54,99,137],"speech":[23],"enhancement":[24],"(SE).":[25],"Different":[26],"from":[27],"conventional":[28,148],"techniques":[29,162],"that":[30,119,163],"directly":[31,47],"estimate":[32,165],"using":[35,133],"deep":[37],"model,":[38],"our":[39,107,120,143],"idea":[40],"is":[41,96,110,122,145],"to":[42,46,66,76,101],"exploit":[43],"ad-hoc":[44],"constraints":[45],"generate":[48],"consistent":[50,69],"pair":[51],"magnitude":[53],"phase.":[55,167],"Specifically,":[56],"proposed":[58,108,156],"forces":[60],"set":[62],"complex":[64],"numbers":[65],"be":[67,77],"short-time":[70],"Fourier":[71],"transform":[72],"(STFT)":[73],"representation,":[74],"i.e.,":[75],"spectrogram":[79],"real":[82],"signal.":[83],"Our":[84],"approach":[85,121,144],"thus":[86],"avoids":[87],"difficulty":[89],"estimating":[91],"original":[93],"phase,":[94],"which":[95],"highly":[97],"unstructured":[98],"sensitive":[100],"time":[102],"shift.":[103],"The":[104],"influence":[105],"first":[111],"assessed":[112],"on":[113,129],"PR":[115],"task,":[116,132],"experimentally":[117],"demonstrating":[118],"viable.":[123],"Next,":[124],"show":[126],"its":[127],"effectiveness":[128],"an":[130],"SE":[131],"both":[134],"VB-DMD":[136],"WSJ0-CHiME3":[138,153],"data":[139],"sets.":[140],"On":[141,150],"VB-DMD,":[142],"competitive":[146],"with":[147],"solutions.":[149],"challenging":[152],"set,":[154],"framework":[157],"compares":[158],"favourably":[159],"over":[160],"those":[161],"explicitly":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}