{"id":"https://openalex.org/W3204950929","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206817","title":"Using Deep Speech Recognition to Evaluate Speech Enhancement Methods","display_name":"Using Deep Speech Recognition to Evaluate Speech Enhancement Methods","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3204950929","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206817","mag":"3204950929"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5064401481","display_name":"Shamoon Siddiqui","orcid":null},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shamoon Siddiqui","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045996251","display_name":"Ghulam Rasool","orcid":"https://orcid.org/0000-0001-8551-0090"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghulam Rasool","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036207748","display_name":"Ravi P. Ramachandran","orcid":"https://orcid.org/0000-0003-0011-4561"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi P. Ramachandran","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105422398","display_name":"Nidhal C. Bouaynaya","orcid":null},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhal C. Bouaynaya","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, New Jersey, USA","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064401481"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":0.7577,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72574062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9998999834060669,"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":0.9962999820709229,"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":0.7895549535751343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7728467583656311},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7052532434463501},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6157333850860596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5865936279296875},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5734290480613708},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5572004318237305},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5031360983848572},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48812493681907654},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.45371660590171814},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4532015919685364},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43545040488243103},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4329088628292084},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4183429777622223},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.41606754064559937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3899584710597992},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24401575326919556},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07302331924438477},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.06352809071540833},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06189107894897461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895549535751343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7728467583656311},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7052532434463501},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6157333850860596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5865936279296875},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5734290480613708},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5572004318237305},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5031360983848572},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48812493681907654},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.45371660590171814},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4532015919685364},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43545040488243103},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4329088628292084},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4183429777622223},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.41606754064559937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3899584710597992},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24401575326919556},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07302331924438477},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.06352809071540833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06189107894897461},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1510355813","https://openalex.org/W1627054999","https://openalex.org/W1647671624","https://openalex.org/W1922655562","https://openalex.org/W1959608418","https://openalex.org/W1968939597","https://openalex.org/W1974387177","https://openalex.org/W1975163393","https://openalex.org/W2015069270","https://openalex.org/W2019965594","https://openalex.org/W2067295501","https://openalex.org/W2099471712","https://openalex.org/W2120987913","https://openalex.org/W2130813098","https://openalex.org/W2138095440","https://openalex.org/W2144404214","https://openalex.org/W2157628442","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2405774341","https://openalex.org/W2507780144","https://openalex.org/W2553276395","https://openalex.org/W2770173563","https://openalex.org/W2892110446","https://openalex.org/W2894295011","https://openalex.org/W2904367110","https://openalex.org/W2910577860","https://openalex.org/W2911579794","https://openalex.org/W2951004968","https://openalex.org/W2951871139","https://openalex.org/W2962770929","https://openalex.org/W2962981281","https://openalex.org/W2963103134","https://openalex.org/W2963204961","https://openalex.org/W2963341071","https://openalex.org/W2963816101","https://openalex.org/W2973188947","https://openalex.org/W2991015288","https://openalex.org/W4253928870","https://openalex.org/W4297817572","https://openalex.org/W4320013936","https://openalex.org/W6603931906","https://openalex.org/W6636671767","https://openalex.org/W6636915900","https://openalex.org/W6687566353","https://openalex.org/W6713658392","https://openalex.org/W6746638498","https://openalex.org/W6755257315","https://openalex.org/W6757146666","https://openalex.org/W6758675244"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2401089611","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W3160071434","https://openalex.org/W2851491717","https://openalex.org/W4252682934","https://openalex.org/W2135485548","https://openalex.org/W2072884270","https://openalex.org/W2373767407"],"abstract_inverted_index":{"Progress":[0],"in":[1,21,142,189,207,229],"speech-related":[2],"tasks":[3,49],"is":[4,145,248],"dependent":[5],"on":[6,105],"the":[7,10,60,69,75,95,106,137,152,161,173,195,245],"quality":[8,117],"of":[9,24,63,94,115,154,164,175,197,221],"speech":[11,25,32,42,70,155,166,250],"signal":[12,43,66,107],"being":[13],"processed.":[14],"While":[15],"much":[16],"progress":[17],"has":[18,50],"been":[19,52,131],"made":[20],"various":[22,198],"aspects":[23],"processing":[26],"(including":[27],"but":[28,118],"not":[29,51,120,217],"limited":[30],"to,":[31],"recognition,":[33],"language":[34],"detection,":[35],"and":[36,73,204],"speaker":[37],"diarization),":[38],"enhancing":[39],"a":[40,64,148,186,205,218,230],"noise-corrupted":[41,65],"as":[44,157,223],"it":[45,158,224],"relates":[46,159,225],"to":[47,58,67,101,123,133,135,146,150,160,226],"those":[48],"rigorously":[53],"evaluated.":[54],"Speech":[55,79],"enhancement":[56,80,156],"aims":[57],"improve":[59],"signal-to-noise":[61],"ratio":[62],"boost":[68],"elements":[71],"(signal)":[72],"reduce":[74],"non-speech":[76],"ones":[77],"(noise).":[78],"techniques":[81],"are":[82,87,112,216],"evaluated":[83],"using":[84],"metrics":[85,103,128,215],"that":[86,180,212,237],"either":[88],"subjective":[89,110,138,176],"(asking":[90],"people":[91],"their":[92],"opinion":[93],"enhanced":[96],"signal)":[97],"or":[98],"objective":[99,127,214],"(attempt":[100],"calculate":[102],"based":[104],"itself).":[108],"The":[109,126],"measures":[111,177],"better":[113],"indicators":[114],"improved":[116],"do":[119],"scale":[121,188],"well":[122],"large":[124,187],"datasets.":[125],"have":[129],"mostly":[130],"constructed":[132],"attempt":[134],"model":[136],"results.":[139],"Our":[140],"goal":[141],"this":[143],"work":[144],"establish":[147],"benchmark":[149],"assess":[151],"improvement":[153,228],"downstream":[162,231,246],"task":[163,247],"automated":[165,191,249],"recognition.":[167,251],"In":[168],"doing":[169],"so,":[170],"we":[171,235],"retain":[172],"qualities":[174],"while":[178],"ensuring":[179],"evaluation":[181],"can":[182],"be":[183,242],"done":[184],"at":[185],"an":[190,227],"fashion.":[192],"We":[193,210],"explore":[194],"impact":[196],"noise":[199,208],"types,":[200],"including":[201],"stationary,":[202],"non-stationary,":[203],"shift":[206],"distribution.":[209],"found":[211],"existing":[213],"strong":[219],"indicator":[220],"performance":[222],"task.":[232],"As":[233],"such,":[234],"believe":[236],"Word":[238],"Error":[239],"Rate":[240],"should":[241],"used":[243],"when":[244]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}