{"id":"https://openalex.org/W2711335087","doi":"https://doi.org/10.1109/icassp.2017.7953226","title":"Speech dereverberation and denoising using complex ratio masks","display_name":"Speech dereverberation and denoising using complex ratio masks","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2711335087","doi":"https://doi.org/10.1109/icassp.2017.7953226","mag":"2711335087"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5054209447","display_name":"Donald S. Williamson","orcid":"https://orcid.org/0000-0002-7997-5403"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald S. Williamson","raw_affiliation_strings":["School of Informatics and Computing, Indiana University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, Ohio State University, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"5590","last_page":"5594"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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/reverberation","display_name":"Reverberation","score":0.7080075740814209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953303217887878},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6562756299972534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6342051029205322},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.582624614238739},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.527023434638977},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.5145913362503052},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5145811438560486},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.43350762128829956},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4129940867424011},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.41233694553375244},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3232663869857788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3226739764213562},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.30740249156951904},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07560980319976807},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0697886049747467},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06639382243156433}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7080075740814209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953303217887878},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6562756299972534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6342051029205322},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.582624614238739},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.527023434638977},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.5145913362503052},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5145811438560486},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.43350762128829956},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4129940867424011},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.41233694553375244},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3232663869857788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3226739764213562},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.30740249156951904},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07560980319976807},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0697886049747467},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06639382243156433},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1536373746","https://openalex.org/W1983812858","https://openalex.org/W1989364685","https://openalex.org/W1991646723","https://openalex.org/W1998648683","https://openalex.org/W2006129368","https://openalex.org/W2010275911","https://openalex.org/W2041498927","https://openalex.org/W2042071805","https://openalex.org/W2045043668","https://openalex.org/W2052667477","https://openalex.org/W2054480978","https://openalex.org/W2055611715","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2084347883","https://openalex.org/W2095072097","https://openalex.org/W2097491464","https://openalex.org/W2243943790","https://openalex.org/W2291877678","https://openalex.org/W4231807801"],"related_works":["https://openalex.org/W2732511158","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889"],"abstract_inverted_index":{"Traditional":[0],"speech":[1,18,95],"separation":[2],"systems":[3],"enhance":[4],"the":[5,60,77,83],"magnitude":[6,24,61],"response":[7],"of":[8,64,82],"noisy":[9,67],"speech.":[10,68],"Recent":[11],"studies,":[12,31],"however,":[13,32],"have":[14,33],"shown":[15],"that":[16,43,57,105,112],"perceptual":[17],"quality":[19],"is":[20,39,107],"significantly":[21],"improved":[22],"when":[23,96],"and":[25,62,66,79,93,111],"phase":[26,37,63,106],"are":[27],"both":[28],"enhanced.":[29],"These":[30],"not":[34],"determined":[35],"if":[36],"enhancement":[38],"beneficial":[40],"in":[41,91],"environments":[42],"contain":[44],"reverberation":[45],"as":[46,48],"well":[47],"noise.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"present":[54],"an":[55],"approach":[56],"jointly":[58],"enhances":[59],"reverberant":[65],"We":[69],"use":[70],"a":[71,99],"deep":[72],"neural":[73],"network":[74],"to":[75,98],"estimate":[76],"real":[78],"imaginary":[80],"components":[81],"complex":[84,113],"ideal":[85],"ratio":[86,114],"mask":[87],"(cIRM),":[88],"which":[89],"results":[90,103],"clean":[92],"anechoic":[94],"applied":[97],"reverberant-noisy":[100],"mixture.":[101],"Our":[102],"show":[104],"important":[108],"for":[109],"dereverberation,":[110],"masking":[115],"outperforms":[116],"related":[117],"methods.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}