{"id":"https://openalex.org/W4392903924","doi":"https://doi.org/10.1109/icassp48485.2024.10448343","title":"Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement","display_name":"Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903924","doi":"https://doi.org/10.1109/icassp48485.2024.10448343"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448343","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012132420","display_name":"George Close","orcid":"https://orcid.org/0000-0002-9478-5421"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"George Close","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Sheffield,UK","Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004802529","display_name":"William Ravenscroft","orcid":"https://orcid.org/0000-0002-0780-3303"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William Ravenscroft","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Sheffield,UK","Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Sheffield,UK","Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Sheffield,UK","Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012132420"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":1.1251,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74633258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"355"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7718218564987183},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6800665855407715},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6752858757972717},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6139965057373047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6103978753089905},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5861522555351257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232414603233337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4976480305194855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46973690390586853},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4345845580101013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718218564987183},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6800665855407715},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6752858757972717},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6139965057373047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6103978753089905},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5861522555351257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232414603233337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4976480305194855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46973690390586853},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4345845580101013},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448343","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2147524299","https://openalex.org/W2897312934","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3023568474","https://openalex.org/W3027008958","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3097777922","https://openalex.org/W3196475561","https://openalex.org/W3197912330","https://openalex.org/W3202278141","https://openalex.org/W3207551191","https://openalex.org/W3209059054","https://openalex.org/W4221143458","https://openalex.org/W4225302959","https://openalex.org/W4292969786","https://openalex.org/W4312959668","https://openalex.org/W4372260337","https://openalex.org/W4372266927","https://openalex.org/W4375868990","https://openalex.org/W4383961998","https://openalex.org/W4386304689","https://openalex.org/W4386764361","https://openalex.org/W4388117238","https://openalex.org/W4389315123","https://openalex.org/W6762114000","https://openalex.org/W6777776875"],"related_works":["https://openalex.org/W4361804730","https://openalex.org/W2142113611","https://openalex.org/W2334467465","https://openalex.org/W2087870008","https://openalex.org/W2162534555","https://openalex.org/W2752178021","https://openalex.org/W2107419853","https://openalex.org/W2143024819","https://openalex.org/W4247159817","https://openalex.org/W2964201926"],"abstract_inverted_index":{"Neural":[0],"network":[1],"based":[2],"approaches":[3,31],"to":[4,9,15,20,74],"speech":[5,126,134],"enhancement":[6,127],"have":[7],"shown":[8],"be":[10,46],"particularly":[11],"powerful,":[12],"being":[13],"able":[14],"leverage":[16],"a":[17,23,84,92],"data-driven":[18],"approach":[19,88,111],"result":[21],"in":[22],"significant":[24],"performance":[25,76,114],"gain":[26],"versus":[27,115],"other":[28],"approaches.":[29],"Such":[30],"are":[32],"reliant":[33],"on":[34,77,95,118],"artificially":[35],"created":[36],"labelled":[37,97],"training":[38],"data":[39,98],"such":[40,65],"that":[41],"the":[42,54,57,119],"neural":[43,107],"model":[44,58,93,136],"can":[45],"trained":[47,94,104],"using":[48,99],"intrusive":[49],"loss":[50],"functions":[51],"which":[52],"compare":[53],"output":[55],"of":[56,64,101],"with":[59],"clean":[60],"reference":[61],"speech.":[62],"Performance":[63],"systems":[66,117],"when":[67],"enhancing":[68],"real-world":[69],"audio":[70],"often":[71],"suffers":[72],"relative":[73],"their":[75],"simulated":[78],"test":[79],"data.":[80],"In":[81],"this":[82],"work,":[83],"non-intrusive":[85],"multi-metric":[86],"prediction":[87,106,143],"is":[89],"introduced,":[90],"wherein":[91],"artificial":[96],"inference":[100],"an":[102],"adversarially":[103],"metric":[105,142],"network.":[108],"The":[109],"proposed":[110],"shows":[112],"improved":[113],"state-of-the-art":[116],"recent":[120],"CHiME-7":[121],"challenge":[122],"unsupervised":[123],"domain":[124],"adaptation":[125],"(UDASE)":[128],"task":[129],"evaluation":[130],"sets.":[131],"Index":[132],"Terms:":[133],"enhancement,":[135],"generalisation,":[137],"generative":[138],"adversarial":[139],"networks,":[140],"conformer,":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}