{"id":"https://openalex.org/W2600045554","doi":"https://doi.org/10.1109/isspit.2016.7886000","title":"A speech enhancement algorithm using computational auditory scene analysis with spectral subtraction","display_name":"A speech enhancement algorithm using computational auditory scene analysis with spectral subtraction","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2600045554","doi":"https://doi.org/10.1109/isspit.2016.7886000","mag":"2600045554"},"language":"en","primary_location":{"id":"doi:10.1109/isspit.2016.7886000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2016.7886000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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/A5102015112","display_name":"Cong Guo","orcid":"https://orcid.org/0000-0001-8906-0103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Guo","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010400765","display_name":"Like Hui","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Like Hui","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.2199,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.45747456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"6","last_page":"10"},"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":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.7976354956626892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554675340652466},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6620150208473206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6511408686637878},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5541834831237793},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5295805931091309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48404306173324585},{"id":"https://openalex.org/keywords/auditory-system","display_name":"Auditory system","score":0.47295495867729187},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4493197202682495},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43635907769203186},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4354185163974762},{"id":"https://openalex.org/keywords/subtraction","display_name":"Subtraction","score":0.4249250888824463},{"id":"https://openalex.org/keywords/background-subtraction","display_name":"Background subtraction","score":0.4141640067100525},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4126831591129303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3936665654182434},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21283036470413208},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19859927892684937},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.15739241242408752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13350871205329895},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0708029568195343}],"concepts":[{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.7976354956626892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554675340652466},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6620150208473206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6511408686637878},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5541834831237793},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5295805931091309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48404306173324585},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.47295495867729187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4493197202682495},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43635907769203186},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4354185163974762},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.4249250888824463},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.4141640067100525},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4126831591129303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3936665654182434},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21283036470413208},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19859927892684937},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.15739241242408752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13350871205329895},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0708029568195343},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspit.2016.7886000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit.2016.7886000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2017608047","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2100495367","https://openalex.org/W2149425615","https://openalex.org/W2285420822"],"related_works":["https://openalex.org/W3100796443","https://openalex.org/W2360086260","https://openalex.org/W3199891340","https://openalex.org/W2358517980","https://openalex.org/W2051363478","https://openalex.org/W1567098080","https://openalex.org/W1990938546","https://openalex.org/W7819095","https://openalex.org/W2890579888","https://openalex.org/W2053365926"],"abstract_inverted_index":{"Computational":[0],"auditory":[1],"scene":[2],"analysis":[3],"(CASA)":[4],"system":[5,20],"is":[6,52],"well":[7],"used":[8],"in":[9,13,114],"speech":[10,94],"enhancement":[11],"area":[12],"recent":[14],"years.":[15],"We":[16],"propose":[17],"a":[18],"new":[19],"that":[21],"combines":[22],"CASA":[23,33],"and":[24,93,117],"spectral":[25],"subtraction":[26],"to":[27,47,53,90],"get":[28],"better":[29],"enhanced":[30],"speech.":[31],"The":[32,44,110],"part":[34],"consists":[35],"of":[36,65,95,105],"the":[37,49,55,63,68,85,106],"latest":[38],"method":[39,61],"deep":[40],"neural":[41],"networks":[42],"(DNNs).":[43],"original":[45],"way":[46],"reconstruct":[48],"denoise":[50],"signal":[51],"use":[54,104],"estimated":[56,86],"masks":[57,88],"with":[58],"direct":[59],"overlap-add":[60],"ignoring":[62],"information":[64,107],"noise":[66,92],"within":[67,108],"frames.":[69,109],"In":[70,98],"our":[71],"system,":[72],"we":[73,101],"estimate":[74],"self-adapted":[75],"thresholds":[76],"for":[77],"each":[78,96],"channel":[79],"by":[80],"Gaussian":[81],"Mixture":[82],"Model":[83],"from":[84],"ratio":[87],"(ERMs)":[89],"separate":[91],"channel.":[97],"this":[99],"way,":[100],"make":[102],"full":[103],"results":[111],"show":[112],"increase":[113],"both":[115],"objective":[116],"subjective":[118],"evaluation.":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}