{"id":"https://openalex.org/W4404295211","doi":"https://doi.org/10.1109/mmsp61759.2024.10743615","title":"Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-Based Speech Enhancement","display_name":"Exploiting Consistency-Preserving Loss and Perceptual Contrast Stretching to Boost SSL-Based Speech Enhancement","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4404295211","doi":"https://doi.org/10.1109/mmsp61759.2024.10743615"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp61759.2024.10743615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","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/A5038491744","display_name":"Muhammad Salman Khan","orcid":"https://orcid.org/0000-0001-9709-8179"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Muhammad Salman Khan","raw_affiliation_strings":["Kore University of Enna,Enna,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna,Enna,Italy","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Kore University of Enna,Enna,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kore University of Enna,Enna,Italy","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071855826","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0009-0007-0974-4873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuo-Hsuan Hung","raw_affiliation_strings":["Academia Sinica,Taipei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taipei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA Corporation,Taipei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Taipei,China","institution_ids":[]}]},{"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/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Università degli Studi di Palermo,Palermo,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università degli Studi di Palermo,Palermo,Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica,Taipei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taipei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8343,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86819651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9758999943733215,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9144999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6652570366859436},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6545248031616211},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6392890810966492},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5889484882354736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5781700015068054},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5613101720809937},{"id":"https://openalex.org/keywords/contrast-enhancement","display_name":"Contrast enhancement","score":0.5165330767631531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31491509079933167},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1162363588809967},{"id":"https://openalex.org/keywords/magnetic-resonance-imaging","display_name":"Magnetic resonance imaging","score":0.08157593011856079},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.0603201687335968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6652570366859436},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6545248031616211},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6392890810966492},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5889484882354736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5781700015068054},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5613101720809937},{"id":"https://openalex.org/C3018181011","wikidata":"https://www.wikidata.org/wiki/Q6849688","display_name":"Contrast enhancement","level":3,"score":0.5165330767631531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31491509079933167},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1162363588809967},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.08157593011856079},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0603201687335968},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp61759.2024.10743615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unipa.it:10447/669903","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/669903","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":0.4300000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1959608418","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2766672686","https://openalex.org/W2900541487","https://openalex.org/W2906042495","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2985607490","https://openalex.org/W3028019732","https://openalex.org/W3036167779","https://openalex.org/W3036601975","https://openalex.org/W3095247787","https://openalex.org/W3097756030","https://openalex.org/W3097777922","https://openalex.org/W3120607380","https://openalex.org/W3163827866","https://openalex.org/W3193917007","https://openalex.org/W3197580070","https://openalex.org/W3197729725","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221143458","https://openalex.org/W4221144097","https://openalex.org/W4224933800","https://openalex.org/W4226390724","https://openalex.org/W4226403810","https://openalex.org/W4232282348","https://openalex.org/W4296069347","https://openalex.org/W4319862462","https://openalex.org/W4380434618","https://openalex.org/W4385807442","https://openalex.org/W4385822340","https://openalex.org/W4385823093","https://openalex.org/W4392904704","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W2163751115","https://openalex.org/W2586608483","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2988088379","https://openalex.org/W2625093041","https://openalex.org/W2733233723","https://openalex.org/W769135352","https://openalex.org/W2415838370","https://openalex.org/W3120218437"],"abstract_inverted_index":{"Self-supervised":[0],"representation":[1],"learning":[2],"(SSL)":[3],"has":[4],"attained":[5],"SOTA":[6,130],"results":[7],"on":[8,110,124],"several":[9,125],"downstream":[10],"speech":[11,15],"tasks,":[12],"but":[13],"SSL-based":[14,119],"enhancement":[16],"(SE)":[17],"solutions":[18,121],"still":[19],"lag":[20],"behind.":[21],"To":[22],"address":[23],"this":[24],"issue,":[25],"we":[26,69],"exploit":[27],"three":[28],"main":[29],"ideas:":[30],"(i)":[31],"Transformer-based":[32],"masking":[33],"generation,":[34],"(ii)":[35],"consistency-preserving":[36],"loss,":[37],"and":[38,59,102],"(iii)":[39],"perceptual":[40,107],"contrast":[41,99],"stretching":[42],"(PCS).":[43],"In":[44],"detail,":[45],"conformer":[46],"layers,":[47],"leveraging":[48],"an":[49],"attention":[50],"mechanism,":[51],"are":[52],"introduced":[53],"to":[54,80,96,106],"effectively":[55],"model":[56],"frame-level":[57],"representations":[58],"obtain":[60],"the":[61,73,78,83,90,98,111,114],"Ideal":[62],"Ratio":[63],"Mask":[64],"(IRM)":[65],"for":[66,82],"SE.":[67],"Moreover,":[68],"incorporate":[70],"consistency":[71],"in":[72],"loss":[74],"function,":[75],"which":[76],"processes":[77],"input":[79,101],"account":[81],"inconsistency":[84],"effects":[85],"of":[86,100,133],"signal":[87],"reconstruction":[88],"from":[89],"spectrogram.":[91],"Finally,":[92],"PCS":[93],"is":[94],"employed":[95],"improve":[97],"target":[103],"features":[104],"according":[105],"importance.":[108],"Evaluated":[109],"VoiceBank-DEMAND":[112],"task,":[113],"proposed":[115],"solution":[116],"outperforms":[117],"previously":[118],"SE":[120],"when":[122],"tested":[123],"objective":[126],"metrics,":[127],"attaining":[128],"a":[129],"PESQ":[131],"score":[132],"3.54.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}