{"id":"https://openalex.org/W2955597484","doi":"https://doi.org/10.1145/3330393.3330427","title":"An Iterative Post-processing Approach for Speech Enhancement","display_name":"An Iterative Post-processing Approach for Speech Enhancement","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2955597484","doi":"https://doi.org/10.1145/3330393.3330427","mag":"2955597484"},"language":"en","primary_location":{"id":"doi:10.1145/3330393.3330427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","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":null,"display_name":"Zhang Huimin","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":true,"raw_author_name":"Zhang Huimin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046221437","display_name":"Xupeng Jia","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":"Jia Xupeng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100417621","display_name":"Dongmei Li","orcid":"https://orcid.org/0000-0002-9014-044X"},"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":"Li Dongmei","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.334,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5469815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"134"},"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":0.9976000189781189,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9947999715805054,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8919668197631836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767157554626465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7669682502746582},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7148409485816956},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6805450916290283},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5195315480232239},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.44625669717788696},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4169842004776001},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.37534865736961365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34861570596694946},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.174024760723114}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8919668197631836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767157554626465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7669682502746582},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7148409485816956},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6805450916290283},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5195315480232239},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.44625669717788696},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4169842004776001},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37534865736961365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34861570596694946},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.174024760723114},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330393.3330427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330393.3330427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1533861849","https://openalex.org/W1974387177","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2086139506","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2171000037","https://openalex.org/W2397226255","https://openalex.org/W2403766732","https://openalex.org/W2748855190","https://openalex.org/W2962866211","https://openalex.org/W4245919820","https://openalex.org/W6600045627","https://openalex.org/W6600751047","https://openalex.org/W6610654676"],"related_works":["https://openalex.org/W2037635165","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W1986772939","https://openalex.org/W2294333436","https://openalex.org/W4200562864","https://openalex.org/W2851491717","https://openalex.org/W2536333783","https://openalex.org/W2168417340","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,51],"has":[2],"been":[3],"widely":[4],"used":[5],"in":[6],"speech":[7,25,37,41,50,82,92,96],"recognition,":[8],"multimedia":[9],"systems":[10],"and":[11,39,43,78,83,94],"hearing":[12],"aids":[13],"etc.":[14],"In":[15],"this":[16],"study,":[17],"we":[18],"explore":[19],"a":[20,48],"new":[21],"post-processing":[22,32,66,88,109,112,124],"strategy":[23,125],"for":[24],"enhancement.":[26,46],"The":[27,114],"main":[28],"goal":[29],"of":[30,80],"proposed":[31,68,87,123],"method":[33,89],"is":[34,58,67],"to":[35,69,104],"reduce":[36],"distortion":[38,97],"improve":[40,127],"quality":[42,79],"intelligibility":[44,77,93],"after":[45],"First,":[47],"masking-based":[49],"system":[52,107],"based":[53],"on":[54,71],"deep":[55],"neural":[56],"network":[57],"implemented.":[59],"Then,":[60],"an":[61],"iterative":[62],"global":[63],"variance":[64],"equalization":[65],"adopt":[70],"estimated":[72],"masks.":[73],"We":[74],"evaluate":[75],"the":[76,86,105,122,128],"enhanced":[81],"observe":[84],"that":[85,121],"achieves":[90],"higher":[91],"less":[95],"at":[98,131],"low":[99],"signal-to-noise":[100],"ratios":[101],"(SNRs)":[102],"comparing":[103],"baseline":[106],"without":[108],"or":[110],"previous":[111],"methods.":[113],"experiments":[115],"under":[116],"unseen":[117],"noises":[118],"also":[119],"show":[120],"can":[126],"model":[129],"generalization":[130],"multiple":[132],"noise":[133],"types.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}