{"id":"https://openalex.org/W4293518750","doi":"https://doi.org/10.1109/icme52920.2022.9858924","title":"Improving Monaural Speech Enhancement with Dynamic Scene Perception Module","display_name":"Improving Monaural Speech Enhancement with Dynamic Scene Perception Module","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518750","doi":"https://doi.org/10.1109/icme52920.2022.9858924"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9858924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9858924","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5101523731","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0001-6381-7657"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian Lan","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050401","display_name":"Jiajia Li","orcid":"https://orcid.org/0000-0003-0330-4264"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajia Li","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090741164","display_name":"Wenxin Tai","orcid":"https://orcid.org/0000-0001-7364-8324"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Tai","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427130","display_name":"Cong Chen","orcid":"https://orcid.org/0000-0003-3499-6312"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101909712","display_name":"J. KANG","orcid":"https://orcid.org/0000-0002-6384-891X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Kang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077109703","display_name":"Qiao Liu","orcid":"https://orcid.org/0000-0002-2573-9544"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101523731"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06761453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9941999912261963,"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/monaural","display_name":"Monaural","score":0.8934890031814575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6902171969413757},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5959909558296204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5477159023284912},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5165528059005737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2829326093196869},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10118219256401062},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06783363223075867}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8934890031814575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902171969413757},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5959909558296204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5477159023284912},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5165528059005737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2829326093196869},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10118219256401062},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06783363223075867},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9858924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9858924","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4586372628","display_name":null,"funder_award_id":"U19B2028,61772117","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G74676583","display_name":null,"funder_award_id":"ZYGX2019J077","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W1978808268","https://openalex.org/W2051428568","https://openalex.org/W2094721231","https://openalex.org/W2128653836","https://openalex.org/W2159202424","https://openalex.org/W2516342150","https://openalex.org/W2884624567","https://openalex.org/W2889442120","https://openalex.org/W2949558265","https://openalex.org/W2963103134","https://openalex.org/W2982101047","https://openalex.org/W3016203918","https://openalex.org/W3030895838","https://openalex.org/W3096008106","https://openalex.org/W3096408984","https://openalex.org/W3097681199","https://openalex.org/W3101327063","https://openalex.org/W3186033197","https://openalex.org/W3209141406","https://openalex.org/W4253928870","https://openalex.org/W6762114000","https://openalex.org/W6767312599","https://openalex.org/W6776224029","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W2401567014","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"aims":[2],"to":[3,30,86],"recover":[4],"clean":[5],"speech":[6],"from":[7],"complex":[8,33,151],"noise":[9,152],"backgrounds.":[10],"This":[11],"paper":[12],"proposes":[13],"a":[14,82],"novel":[15],"information":[16],"processing":[17],"module":[18,23],"dubbed":[19],"dynamic":[20,66],"scene":[21,67,79],"perception":[22],"(DSPM)":[24],"that":[25,44],"can":[26],"help":[27],"existing":[28,138],"systems":[29],"accommodate":[31],"various":[32,147],"scenarios.":[34,153],"The":[35],"inspiration":[36],"of":[37,47,61,90,109,132],"DSPM":[38,59],"is":[39],"based":[40],"on":[41,120],"the":[42,48,70,78,88,98,102,107,110,121,130,137],"observation":[43],"different":[45,52,55],"regions":[46],"noisy":[49],"spectrum":[50],"in":[51],"scenarios":[53],"have":[54],"enhancing":[56],"requirements.":[57],"Concretely,":[58],"consists":[60],"two":[62],"parts,":[63],"one":[64],"for":[65,72],"estimation,":[68],"and":[69,124,150],"other":[71],"adaptive":[73],"region":[74,99,112],"perception.":[75],"In":[76],"particular,":[77],"estimator":[80],"utilizes":[81],"spectrum-energy-based":[83],"attention":[84],"mechanism":[85],"obtain":[87],"coefficients":[89],"each":[91,96],"convolution":[92],"kernel.":[93],"Then,":[94],"at":[95],"position\u2019":[97],"perceptron":[100],"chooses":[101],"corresponding":[103],"kernels":[104],"by":[105],"considering":[106],"requirements":[108],"current":[111],"(preserve":[113],"vocals":[114],"or":[115],"suppress":[116],"noise).":[117],"Systematic":[118],"evaluations":[119],"TIMIT":[122],"corpus":[123],"Voice":[125],"Bank":[126],"+":[127],"DEMAND":[128],"demonstrate":[129],"effectiveness":[131],"our":[133,140],"method.":[134],"Compared":[135],"with":[136],"systems,":[139],"proposed":[141],"method":[142],"achieved":[143],"better":[144],"performance":[145],"under":[146],"SNR":[148],"conditions":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-08-30T00:00:00"}