{"id":"https://openalex.org/W4387010482","doi":"https://doi.org/10.1109/taslp.2023.3318965","title":"Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments","display_name":"Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387010482","doi":"https://doi.org/10.1109/taslp.2023.3318965"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3318965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3318965","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5103167575","display_name":"Philippe Gonzalez","orcid":"https://orcid.org/0009-0006-4965-3514"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Philippe Gonzalez","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0009-0006-4965-3514","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064146030","display_name":"Tommy Sonne Alstr\u00f8m","orcid":"https://orcid.org/0000-0003-0941-3146"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tommy Sonne Alstr\u00f8m","raw_affiliation_strings":["Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0941-3146","affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052043106","display_name":"Tobias May","orcid":"https://orcid.org/0000-0002-5463-5509"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Tobias May","raw_affiliation_strings":["Department of Health Technology, Technical University of Denmark, Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-5463-5509","affiliations":[{"raw_affiliation_string":"Department of Health Technology, Technical University of Denmark, Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":2.7835,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91751848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3390","last_page":"3403"},"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":0.9990000128746033,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9975000023841858,"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/generalization","display_name":"Generalization","score":0.7947754859924316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365978956222534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.573529839515686},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5565019845962524},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5051830410957336},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4862433969974518},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.4488461911678314},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4294961988925934},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.42710593342781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39423102140426636},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21776026487350464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15629318356513977},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10103604197502136}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7947754859924316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365978956222534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.573529839515686},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5565019845962524},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5051830410957336},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4862433969974518},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.4488461911678314},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4294961988925934},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.42710593342781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39423102140426636},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21776026487350464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15629318356513977},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10103604197502136},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3318965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3318965","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1967300041","https://openalex.org/W1971281497","https://openalex.org/W1974387177","https://openalex.org/W1985029311","https://openalex.org/W1997836753","https://openalex.org/W2015469795","https://openalex.org/W2022870009","https://openalex.org/W2023701017","https://openalex.org/W2031834500","https://openalex.org/W2044063703","https://openalex.org/W2044893557","https://openalex.org/W2054480978","https://openalex.org/W2057200980","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2095705004","https://openalex.org/W2114218864","https://openalex.org/W2130283666","https://openalex.org/W2132510525","https://openalex.org/W2138939691","https://openalex.org/W2148154194","https://openalex.org/W2148577181","https://openalex.org/W2159202424","https://openalex.org/W2167314872","https://openalex.org/W2168379380","https://openalex.org/W2199505332","https://openalex.org/W2289394825","https://openalex.org/W2364134690","https://openalex.org/W2398758402","https://openalex.org/W2404126548","https://openalex.org/W2514828952","https://openalex.org/W2516001803","https://openalex.org/W2550397165","https://openalex.org/W2626775259","https://openalex.org/W2678916739","https://openalex.org/W2766439643","https://openalex.org/W2804382237","https://openalex.org/W2808631503","https://openalex.org/W2884585870","https://openalex.org/W2889442120","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2961183107","https://openalex.org/W2962866211","https://openalex.org/W2963047834","https://openalex.org/W2963587345","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3015312544","https://openalex.org/W3015338123","https://openalex.org/W3027637851","https://openalex.org/W3034408878","https://openalex.org/W3035790469","https://openalex.org/W3037492894","https://openalex.org/W3049430014","https://openalex.org/W3094911989","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3120954100","https://openalex.org/W3166682767","https://openalex.org/W3175215201","https://openalex.org/W3209797185","https://openalex.org/W3212348395","https://openalex.org/W4213196139","https://openalex.org/W4225309689","https://openalex.org/W4231807801","https://openalex.org/W4232282348","https://openalex.org/W4232992964","https://openalex.org/W4372349390","https://openalex.org/W4385245566","https://openalex.org/W4385822821","https://openalex.org/W4393761487","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6639824700","https://openalex.org/W6656414902","https://openalex.org/W6674330103","https://openalex.org/W6680324615","https://openalex.org/W6738884980","https://openalex.org/W6739898779","https://openalex.org/W6739901393","https://openalex.org/W6753412334","https://openalex.org/W6757632829","https://openalex.org/W6777701575","https://openalex.org/W6796913975"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W1656519308","https://openalex.org/W4224270619","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2579722767","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W1982169876"],"abstract_inverted_index":{"The":[0,112,180,203],"acoustic":[1],"variability":[2,37],"of":[3,19,61,97,142,152,161,173,213,274],"noisy":[4],"and":[5,23,31,53,166,194,221,240,268],"reverberant":[6],"speech":[7,44,99,235],"mixtures":[8],"is":[9,68,182,206],"influenced":[10],"by":[11,71,188,246],"multiple":[12,191,249],"factors,":[13],"such":[14,130],"as":[15,136],"the":[16,20,24,27,32,51,59,62,73,89,95,98,110,127,140,143,150,153,159,177,200,210,229,232,275],"spectro-temporal":[17],"characteristics":[18],"target":[21],"speaker":[22],"interfering":[25],"noise,":[26,193],"signal-to-noise":[28],"ratio":[29],"(SNR)":[30],"room":[33,82,241],"characteristics.":[34],"This":[35,146],"large":[36],"poses":[38],"a":[39,48,76,116,122,137,170,185,214],"major":[40],"challenge":[41],"for":[42,139,226],"learning-based":[43],"enhancement":[45,100],"systems,":[46],"since":[47],"mismatch":[49],"between":[50],"training":[52,247],"testing":[54,72],"conditions":[55,67,267],"can":[56,102,107,133,243,269],"substantially":[57,108,263],"reduce":[58],"performance":[60,175,230,257,262],"system.":[63,277],"Generalization":[64],"to":[65,148,168,197,208,272],"unseen":[66],"typically":[69],"assessed":[70],"system":[74],"with":[75,163],"new":[77,164,171],"speech,":[78,192],"noise":[79,239],"or":[80],"binaural":[81],"impulse":[83],"response":[84],"(BRIR)":[85],"database":[86],"different":[87],"from":[88,158],"one":[90],"used":[91,135],"during":[92],"training.":[93],"However,":[94],"difficulty":[96,141,157],"task":[101,156],"change":[103,154],"across":[104],"databases,":[105],"which":[106],"influence":[109],"results.":[111],"present":[113],"study":[114],"introduces":[115],"generalization":[117,174,178,201,211,242],"assessment":[118],"framework":[119,205],"that":[120,131,225,273],"uses":[121],"reference":[123],"model":[124],"trained":[125],"on":[126,248],"test":[128,144],"condition,":[129],"it":[132],"be":[134,244],"proxy":[138],"condition.":[145],"allows":[147],"disentangle":[149],"effect":[151,160],"in":[155,184,234,258,265],"dealing":[162],"data,":[165],"thus":[167],"define":[169],"measure":[172],"termed":[176],"gap.":[179,202],"procedure":[181],"repeated":[183],"cross-validation":[186],"fashion":[187],"cycling":[189],"through":[190],"BRIR":[195],"databases":[196],"accurately":[198],"estimate":[199],"proposed":[204],"applied":[207],"evaluate":[209],"potential":[212],"feedforward":[215],"neural":[216],"network":[217],"(FFNN),":[218],"Conv-TasNet,":[219],"DCCRN":[220],"MANNER.":[222],"We":[223],"find":[224],"all":[227],"models,":[228],"degrades":[231],"most":[233],"mismatches,":[236],"while":[237,252],"good":[238],"achieved":[245],"databases.":[250],"Moreover,":[251],"recent":[253],"models":[254],"show":[255],"higher":[256],"matched":[259],"conditions,":[260],"their":[261],"decreases":[264],"mismatched":[266],"become":[270],"inferior":[271],"FFNN-based":[276]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}