{"id":"https://openalex.org/W4392904334","doi":"https://doi.org/10.1109/icassp48485.2024.10448341","title":"Pre-Echo Reduction in Transform Audio Coding via Temporal Envelope Control with Machine Learning Based Estimation","display_name":"Pre-Echo Reduction in Transform Audio Coding via Temporal Envelope Control with Machine Learning Based Estimation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904334","doi":"https://doi.org/10.1109/icassp48485.2024.10448341"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448341","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100413746","display_name":"Jae-Won Kim","orcid":"https://orcid.org/0000-0003-1608-5849"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Won Kim","raw_affiliation_strings":["Kwangwoon University,Seoul,Korea","Kwangwoon University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Seoul,Korea","institution_ids":["https://openalex.org/I161024014"]},{"raw_affiliation_string":"Kwangwoon University, Seoul, Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083069595","display_name":"Byeongho Jo","orcid":"https://orcid.org/0000-0002-3785-6406"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongho Jo","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea","Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071537541","display_name":"Seungkwon Beack","orcid":"https://orcid.org/0000-0002-6254-2062"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkwon Beack","raw_affiliation_strings":["Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea","Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI),Daejeon,Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056157686","display_name":"Hochong Park","orcid":"https://orcid.org/0000-0003-1600-6610"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hochong Park","raw_affiliation_strings":["Kwangwoon University,Seoul,Korea","Kwangwoon University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Seoul,Korea","institution_ids":["https://openalex.org/I161024014"]},{"raw_affiliation_string":"Kwangwoon University, Seoul, Korea","institution_ids":["https://openalex.org/I161024014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4171,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47689634,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900120377540588},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6455954909324646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6237565279006958},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6100399494171143},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.525382399559021},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4933456480503082},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.49050062894821167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4504871070384979},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4305436313152313},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42415156960487366},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4215494990348816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3441760540008545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17304173111915588},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13076823949813843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900120377540588},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6455954909324646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6237565279006958},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6100399494171143},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.525382399559021},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4933456480503082},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.49050062894821167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4504871070384979},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4305436313152313},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42415156960487366},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4215494990348816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3441760540008545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17304173111915588},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13076823949813843},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448341","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1495277531","https://openalex.org/W1963699091","https://openalex.org/W2089473323","https://openalex.org/W2117366609","https://openalex.org/W2170057365","https://openalex.org/W2504165400","https://openalex.org/W2605994195","https://openalex.org/W2889428811","https://openalex.org/W2919115771","https://openalex.org/W2936557804","https://openalex.org/W3015567712","https://openalex.org/W3015780049","https://openalex.org/W3161744562","https://openalex.org/W3214758449","https://openalex.org/W3215615641","https://openalex.org/W4285186333","https://openalex.org/W4372260101","https://openalex.org/W4372270198","https://openalex.org/W6629271464","https://openalex.org/W6639051950"],"related_works":["https://openalex.org/W2126742497","https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481","https://openalex.org/W2109142991"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,36,46,60,115],"new":[4,116],"method":[5,23,41,93,130],"for":[6,119],"pre-echo":[7],"reduction":[8],"in":[9,98],"transform-based":[10],"audio":[11],"coding":[12,117],"by":[13],"controlling":[14],"the":[15,19,66,73,79,86,103,128,142],"temporal":[16,28,32,48,74],"envelope":[17,29,33],"of":[18,35,141],"waveform.":[20],"The":[21,39,91],"proposed":[22,40,92,129],"comprises":[24],"two":[25],"operating":[26],"modes:":[27],"flattening":[30],"and":[31,56,71,88,107],"correction":[34],"target":[37,67],"signal.":[38],"estimates":[42],"signal":[43,61,68,83],"levels":[44],"with":[45],"low":[47],"resolution":[49],"from":[50,95],"side":[51],"information":[52],"using":[53],"machine":[54],"learning":[55],"converts":[57],"them":[58],"into":[59],"to":[62,65,69,81,134,139],"be":[63],"applied":[64],"flatten":[70],"correct":[72],"envelope.":[75],"It":[76],"also":[77],"adjusts":[78],"signals":[80],"maintain":[82],"continuity":[84],"between":[85],"non-transient":[87],"transient":[89],"frames.":[90],"differs":[94],"conventional":[96],"methods":[97],"that":[99,127,140],"it":[100,112],"directly":[101],"modifies":[102],"waveform":[104],"before":[105],"encoding":[106],"after":[108],"decoding,":[109],"which":[110],"makes":[111],"useful":[113],"as":[114],"tool":[118],"legacy":[120],"codecs.":[121],"A":[122],"subjective":[123],"performance":[124],"evaluation":[125],"confirms":[126],"uses":[131],"fewer":[132],"bits":[133],"provide":[135],"sound":[136],"quality":[137],"equivalent":[138],"short-window":[143],"transform.1":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}