{"id":"https://openalex.org/W3103003256","doi":"https://doi.org/10.1109/taslp.2020.3036783","title":"A Cross-Entropy-Guided Measure (CEGM) for Assessing Speech Recognition Performance and Optimizing DNN-Based Speech Enhancement","display_name":"A Cross-Entropy-Guided Measure (CEGM) for Assessing Speech Recognition Performance and Optimizing DNN-Based Speech Enhancement","publication_year":2020,"publication_date":"2020-11-12","ids":{"openalex":"https://openalex.org/W3103003256","doi":"https://doi.org/10.1109/taslp.2020.3036783","mag":"3103003256"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3036783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036783","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/A5100704805","display_name":"Li Chai","orcid":"https://orcid.org/0000-0001-7906-9913"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7906-9913","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039181878","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-5437-4946"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1892-2551","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":5.9392,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97279095,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"106","last_page":"117"},"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":0.9986000061035156,"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":0.9973999857902527,"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/speech-recognition","display_name":"Speech recognition","score":0.7269493341445923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7191319465637207},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6062293648719788},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5415272116661072},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5248741507530212},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4610769748687744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45661965012550354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3850853443145752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3680017292499542},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2397875189781189}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7269493341445923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7191319465637207},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6062293648719788},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5415272116661072},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5248741507530212},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4610769748687744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45661965012550354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3850853443145752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3680017292499542},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2397875189781189},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3036783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3036783","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":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":"\u57fa\u4e8e\u56de\u5f52\u795e\u7ecf\u7f51\u7edc\u7684\u8bed\u97f3\u5206\u79bb\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61671422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W584635876","https://openalex.org/W1494198834","https://openalex.org/W1523493493","https://openalex.org/W1524333225","https://openalex.org/W1598508708","https://openalex.org/W1686810756","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1975163393","https://openalex.org/W1988961123","https://openalex.org/W1995536493","https://openalex.org/W1999841894","https://openalex.org/W2031692264","https://openalex.org/W2039716246","https://openalex.org/W2044893557","https://openalex.org/W2045956438","https://openalex.org/W2062164080","https://openalex.org/W2069681747","https://openalex.org/W2103264249","https://openalex.org/W2113556376","https://openalex.org/W2115086266","https://openalex.org/W2115415333","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2131342762","https://openalex.org/W2137988753","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2151415191","https://openalex.org/W2153038597","https://openalex.org/W2158501878","https://openalex.org/W2160815625","https://openalex.org/W2168379380","https://openalex.org/W2287242746","https://openalex.org/W2296167893","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2491975496","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2560747691","https://openalex.org/W2584390378","https://openalex.org/W2613006358","https://openalex.org/W2653598178","https://openalex.org/W2711861986","https://openalex.org/W2735006420","https://openalex.org/W2889500840","https://openalex.org/W2899829828","https://openalex.org/W2937998856","https://openalex.org/W2962727772","https://openalex.org/W2962835968","https://openalex.org/W2962843322","https://openalex.org/W2962892438","https://openalex.org/W2963045393","https://openalex.org/W2963458655","https://openalex.org/W2963828919","https://openalex.org/W2969917057","https://openalex.org/W2972320711","https://openalex.org/W2972686263","https://openalex.org/W2972990825","https://openalex.org/W2973050374","https://openalex.org/W3147539069","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6638908295","https://openalex.org/W6677416784","https://openalex.org/W6682351671"],"related_works":["https://openalex.org/W2770665941","https://openalex.org/W2309273277","https://openalex.org/W3096184950","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W1967477266","https://openalex.org/W2547793174"],"abstract_inverted_index":{"A":[0],"new":[1],"cross-entropy-guided":[2],"measure":[3],"(CEGM)":[4],"is":[5,33,96,168],"proposed":[6,31],"to":[7,98,103,111,171,184,213],"indirectly":[8],"assess":[9],"accuracies":[10,143],"of":[11,16,65,76,81,144,179],"automatic":[12],"speech":[13,18,21,130,193,198,216,219],"recognition":[14],"(ASR)":[15],"degraded":[17],"with":[19,162,221,227],"a":[20,40,47,57,93],"enhancement":[22,135,194,199,223],"front-end":[23,134],"and":[24,55,67,92,173,217],"without":[25],"directly":[26],"performing":[27],"ASR":[28,84,147,180,225],"experiments.":[29],"The":[30],"CEGM":[32,59,156],"calculated":[34],"in":[35,232],"three":[36],"steps,":[37],"namely:":[38],"(1)":[39],"low-level":[41],"representations":[42,64,91],"via":[43],"feature":[44],"extraction,":[45],"(2)":[46],"high-level":[48,63,90],"nonlinear":[49],"mapping":[50],"using":[51],"an":[52,122],"acoustic":[53,79,230],"model,":[54],"(3)":[56],"final":[58],"calculation":[60],"between":[61],"the":[62,82,89,100,113,133,142,145,159,175,185,203,206],"clean":[66],"enhanced":[68,218],"speech.":[69],"Specifically,":[70],"state":[71],"posterior":[72],"probabilities":[73],"from":[74],"outputs":[75],"conventional":[77,114],"hybrid":[78],"model":[80,136],"target":[83],"system":[85],"are":[86],"adopted":[87],"as":[88,121],"cross-entropy":[94],"criterion":[95,120],"used":[97,110,190],"calculate":[99],"CEGM.":[101],"Due":[102],"CEGM's":[104],"differentiability,":[105],"it":[106],"can":[107,137],"also":[108],"be":[109,138],"replace":[112],"minimum":[115],"mean":[116],"squared":[117],"error":[118,164],"(MMSE)":[119],"objective":[123],"function":[124],"for":[125,191,224],"deep":[126,234],"neural":[127],"network":[128],"(DNN)-based":[129],"enhancement.":[131],"Therefore,":[132],"optimized":[139],"towards":[140],"improving":[141],"back-end":[146],"system.":[148],"Experiments":[149],"on":[150,205],"single-channel":[151],"CHiME-4":[152,207],"Challenge":[153],"show":[154],"that":[155],"yields":[157],"consistently":[158],"highest":[160],"correlations":[161],"word":[163],"rate":[165],"(WER)":[166],"which":[167],"often":[169],"costly":[170],"calculate,":[172],"achieves":[174],"most":[176],"accurate":[177],"assessment":[178],"performance":[181],"when":[182,211],"compared":[183,212],"perceptual":[186],"evaluation":[187],"metrics":[188],"commonly":[189],"assessing":[192],"performance.":[195],"Furthermore,":[196],"CEGM-optimized":[197],"could":[200],"effectively":[201],"reduce":[202],"WER":[204],"real":[208],"test":[209],"set":[210],"unprocessed":[214],"noisy":[215],"obtained":[220],"MMSE-optimized":[222],"systems":[226],"fixed":[228],"multi-condition":[229],"models":[231],"various":[233],"architectures.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}