{"id":"https://openalex.org/W3016120385","doi":"https://doi.org/10.1109/icassp40776.2020.9054254","title":"Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement","display_name":"Weighted Speech Distortion Losses for Neural-Network-Based Real-Time Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016120385","doi":"https://doi.org/10.1109/icassp40776.2020.9054254","mag":"3016120385"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5104037412","display_name":"Yangyang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yangyang Xia","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan K. A. Reddy","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033701513","display_name":"Harishchandra Dubey","orcid":"https://orcid.org/0000-0003-0476-3884"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harishchandra Dubey","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104037412"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":12.9503,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.99319461,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"871","last_page":"875"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958000183105469,"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":0.7911320924758911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7332756519317627},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7158352136611938},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6722648739814758},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6550496816635132},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5919176936149597},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.48857173323631287},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4613480865955353},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46099379658699036},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.46067580580711365},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4589570164680481},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4516165256500244},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44027960300445557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38820594549179077},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.36538371443748474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3425060510635376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11628419160842896},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.10331156849861145},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07629281282424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911320924758911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7332756519317627},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7158352136611938},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6722648739814758},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6550496816635132},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5919176936149597},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.48857173323631287},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4613480865955353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46099379658699036},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.46067580580711365},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4589570164680481},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4516165256500244},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44027960300445557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38820594549179077},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.36538371443748474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3425060510635376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11628419160842896},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.10331156849861145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07629281282424927},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"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":39,"referenced_works":["https://openalex.org/W217932999","https://openalex.org/W1483052920","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2110120390","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2157331557","https://openalex.org/W2169147844","https://openalex.org/W2397226255","https://openalex.org/W2402901296","https://openalex.org/W2486913545","https://openalex.org/W2605589342","https://openalex.org/W2804690068","https://openalex.org/W2889133076","https://openalex.org/W2889442120","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2962843322","https://openalex.org/W2962946126","https://openalex.org/W2963341071","https://openalex.org/W2963868408","https://openalex.org/W2964058413","https://openalex.org/W2967086982","https://openalex.org/W2972443522","https://openalex.org/W2973133192","https://openalex.org/W3123318516","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4289665794","https://openalex.org/W6667372801","https://openalex.org/W6712317276","https://openalex.org/W6713117669","https://openalex.org/W6735429107","https://openalex.org/W6766766128"],"related_works":["https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W1986772939","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W4200596008","https://openalex.org/W2294333436","https://openalex.org/W2536333783","https://openalex.org/W2168417340"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"several":[3],"aspects":[4],"of":[5,19,66,99,111],"training":[6],"a":[7,31,39,43,124],"RNN":[8,32],"(recurrent":[9],"neural":[10],"network)":[11],"that":[12,33,59],"impact":[13,98],"the":[14,64,97,108,120],"objective":[15,81,109],"and":[16,83,86,102,123],"subjective":[17,117],"quality":[18,82,110],"enhanced":[20,112],"speech":[21,25,36,67],"for":[22,119],"real-time":[23,126],"single-channel":[24],"enhancement.":[26],"Specifically,":[27],"we":[28,95,115],"focus":[29],"on":[30,38,107],"enhances":[34],"short-time":[35],"spectra":[37],"single-frame-in,":[40],"single-frame-out":[41],"basis,":[42],"framework":[44],"adopted":[45],"by":[46,78],"most":[47],"classical":[48],"signal":[49],"processing":[50],"methods.":[51,92],"We":[52],"propose":[53],"two":[54],"novel":[55],"mean-squared-error-based":[56],"learning":[57],"objectives":[58],"enable":[60],"separate":[61],"control":[62],"over":[63],"importance":[65],"distortion":[68],"versus":[69],"noise":[70],"reduction.":[71],"The":[72],"proposed":[73,121],"loss":[74],"functions":[75],"are":[76],"evaluated":[77],"widely":[79],"accepted":[80],"intelligibility":[84],"measures":[85],"compared":[87],"to":[88],"other":[89],"competitive":[90],"online":[91],"In":[93],"addition,":[94],"study":[96],"feature":[100],"normalization":[101],"varying":[103],"batch":[104],"sequence":[105],"lengths":[106],"speech.":[113],"Finally,":[114],"show":[116],"ratings":[118],"approach":[122],"state-of-the-art":[125],"RNN-based":[127],"method.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":15}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}