{"id":"https://openalex.org/W2797110164","doi":"https://doi.org/10.1109/icassp.2018.8462126","title":"A Study of Training Targets for Deep Neural Network-Based Speech Enhancement Using Noise Prediction","display_name":"A Study of Training Targets for Deep Neural Network-Based Speech Enhancement Using Noise Prediction","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2797110164","doi":"https://doi.org/10.1109/icassp.2018.8462126","mag":"2797110164"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050801227","display_name":"Babafemi O. Odelowo","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Babafemi O. Odelowo","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437141","display_name":"David V. Anderson","orcid":"https://orcid.org/0000-0002-8571-4613"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David V. Anderson","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5409","last_page":"5413"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7757967710494995},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7421776056289673},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7220206260681152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6938403248786926},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.598436176776886},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5590006709098816},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5496042370796204},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48750779032707214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4421643614768982},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4347915053367615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3608637750148773},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.231736958026886},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06217417120933533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757967710494995},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7421776056289673},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7220206260681152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6938403248786926},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.598436176776886},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5590006709098816},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5496042370796204},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48750779032707214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4421643614768982},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4347915053367615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3608637750148773},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.231736958026886},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06217417120933533},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W104438260","https://openalex.org/W1532581717","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1968939597","https://openalex.org/W1989034586","https://openalex.org/W2013608223","https://openalex.org/W2035424729","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2156387975","https://openalex.org/W2237671050","https://openalex.org/W2404892923","https://openalex.org/W2516342150","https://openalex.org/W2783984851","https://openalex.org/W3147539069","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W6604282513","https://openalex.org/W6632030081","https://openalex.org/W6633117090","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W3043214604","https://openalex.org/W1505346162","https://openalex.org/W2117416982","https://openalex.org/W2135485548","https://openalex.org/W2092735486","https://openalex.org/W2231565466","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Several":[0],"architectures":[1],"have":[2],"been":[3],"proposed":[4],"for":[5],"deep":[6],"neural":[7],"network":[8,81],"(DNN)-based":[9],"speech":[10,22],"enhancement;":[11],"however,":[12],"these":[13],"all":[14],"utilize":[15],"training":[16,33],"targets":[17,34,57],"related":[18],"to":[19,45,60],"the":[20,29,42,55,61,66,74,79,112],"clean":[21],"signal.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"evaluate":[28],"performance":[30],"of":[31,84],"several":[32],"in":[35,65,82,90,100,107,115],"a":[36,46],"noise-prediction":[37,43,67],"DNN":[38],"framework":[39,44],"and":[40,87],"compare":[41],"conventional":[47],"speech-prediction":[48,80],"network.":[49],"Objective":[50],"test":[51],"results":[52,70],"show":[53,72],"that":[54,73],"mask-based":[56],"are":[58],"superior":[59],"spectral":[62],"magnitude":[63],"target":[64,77,96,114],"framework.":[68],"The":[69,94],"also":[71,98],"best":[75],"noise":[76,92,95,102],"outperforms":[78],"terms":[83],"objective":[85,108,116],"quality":[86],"intelligibility":[88],"metrics":[89],"seen":[91],"conditions.":[93],"is":[97],"competitive":[99],"unseen":[101],"conditions,":[103],"performing":[104],"slightly":[105],"worse":[106],"quality,":[109],"but":[110],"outperforming":[111],"speech-based":[113],"intelligibility.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}