{"id":"https://openalex.org/W3194323795","doi":"https://doi.org/10.21437/interspeech.2021-1973","title":"Speech Denoising with Auditory Models","display_name":"Speech Denoising with Auditory Models","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3194323795","doi":"https://doi.org/10.21437/interspeech.2021-1973","mag":"3194323795"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1973","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.10706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005640735","display_name":"Mark R. Saddler","orcid":"https://orcid.org/0000-0002-2698-7275"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark R. Saddler","raw_affiliation_strings":["McGovern Institute for Brain Research, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"McGovern Institute for Brain Research, Cambridge, United States","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067381155","display_name":"Andrew Francl","orcid":"https://orcid.org/0000-0001-6417-7866"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Francl","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045484439","display_name":"Jenelle Feather","orcid":"https://orcid.org/0000-0001-9753-2393"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenelle Feather","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030425371","display_name":"Kaizhi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaizhi Qian","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354733","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-8540-1254"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110628266","display_name":"Josh H. McDermott","orcid":"https://orcid.org/0000-0002-3965-2503"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh H. McDermott","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005640735"],"corresponding_institution_ids":["https://openalex.org/I144112489"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10200658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2681","last_page":"2685"},"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":0.9993000030517578,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7491372227668762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216861248016357},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.639788806438446},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6253556609153748},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6173826456069946},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.529793918132782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5232726335525513},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5179376006126404},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5087106823921204},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5030376315116882},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49747756123542786},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49354255199432373},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45800209045410156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3930853605270386},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07867780327796936},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.055596500635147095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.054878175258636475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491372227668762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216861248016357},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.639788806438446},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6253556609153748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6173826456069946},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.529793918132782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5232726335525513},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5179376006126404},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5087106823921204},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5030376315116882},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49747756123542786},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49354255199432373},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45800209045410156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3930853605270386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07867780327796936},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.055596500635147095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.054878175258636475},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1973","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.10706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10706","pdf_url":"https://arxiv.org/pdf/2011.10706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/150013","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/150013","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/150013/2/2011.10706.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"mag:3194323795","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.10706.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.10706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.10706","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.10706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.10706","pdf_url":"https://arxiv.org/pdf/2011.10706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3194323795.pdf","grobid_xml":"https://content.openalex.org/works/W3194323795.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1556219185","https://openalex.org/W2008415856","https://openalex.org/W2050758723","https://openalex.org/W2062663442","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2274405424","https://openalex.org/W2339294230","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2735131873","https://openalex.org/W2800311957","https://openalex.org/W2902132730","https://openalex.org/W2922023527","https://openalex.org/W2943554574","https://openalex.org/W2951506741","https://openalex.org/W2952218014","https://openalex.org/W2962785568","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963248464","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963453742","https://openalex.org/W2970540112","https://openalex.org/W2972443522","https://openalex.org/W2982030720","https://openalex.org/W2988817345","https://openalex.org/W3096159803","https://openalex.org/W3096992656","https://openalex.org/W3097934054","https://openalex.org/W3109018774","https://openalex.org/W3163827866"],"related_works":["https://openalex.org/W3110398235","https://openalex.org/W2577762507","https://openalex.org/W3087443678","https://openalex.org/W3004146833","https://openalex.org/W2958646611","https://openalex.org/W2402901296","https://openalex.org/W2076462394","https://openalex.org/W3121029767","https://openalex.org/W2515372520","https://openalex.org/W3101133222","https://openalex.org/W2885130944","https://openalex.org/W2888868298","https://openalex.org/W3210740416","https://openalex.org/W3109018774","https://openalex.org/W3149824848","https://openalex.org/W2790109708","https://openalex.org/W2964207404","https://openalex.org/W2750143381","https://openalex.org/W3163906773","https://openalex.org/W2945998549"],"abstract_inverted_index":{"Contemporary":[0],"speech":[1,15,73,148],"enhancement":[2],"predominantly":[3],"relies":[4],"on":[5],"audio":[6,68,76,90],"transforms":[7,98],"that":[8,78,143,152,160],"are":[9],"trained":[10,66,106],"to":[11,40,54,70,74,107,136],"reconstruct":[12,108],"a":[13,121],"clean":[14,94,109],"waveform.":[16],"The":[17,96,140],"development":[18],"of":[19,30],"high-performing":[20],"neural":[21,52],"network":[22],"sound":[23],"recognition":[24],"systems":[25],"has":[26],"raised":[27],"the":[28,80,83,88,92,132,137],"possibility":[29],"using":[31,116,128],"deep":[32,51,84,117,138,144],"feature":[33,85,118],"representations":[34,86],"as":[35],"'perceptual'":[36],"losses":[37,129],"with":[38],"which":[39],"train":[41],"denoising":[42],"systems.":[43],"We":[44,64],"explored":[45],"their":[46],"utility":[47],"by":[48,127],"first":[49],"training":[50],"networks":[53],"classify":[55],"either":[56],"spoken":[57],"words":[58],"or":[59],"environmental":[60],"sounds":[61],"from":[62,131],"audio.":[63,95],"then":[65],"an":[67,75],"transform":[69],"map":[71],"noisy":[72],"waveform":[77],"minimized":[79],"difference":[81],"in":[82],"between":[87],"output":[89],"and":[91,111],"corresponding":[93],"resulting":[97],"removed":[99],"noise":[100],"substantially":[101],"better":[102],"than":[103],"baseline":[104],"methods":[105,115],"waveforms,":[110],"also":[112],"outperformed":[113],"previous":[114],"losses.":[119],"However,":[120],"similar":[122],"benefit":[123],"was":[124],"obtained":[125],"simply":[126],"derived":[130],"filter":[133],"bank":[134],"inputs":[135],"networks.":[139],"results":[141],"show":[142],"features":[145],"can":[146],"guide":[147],"enhancement,":[149],"but":[150],"suggest":[151],"they":[153],"do":[154,161],"not":[155,162],"yet":[156],"outperform":[157],"simple":[158],"alternatives":[159],"involve":[163],"learned":[164],"features.":[165]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}