{"id":"https://openalex.org/W4386764852","doi":"https://doi.org/10.1109/waspaa58266.2023.10248056","title":"Masked Frequency Modeling for Improving Packet Loss Concealment in Speech Transmission Systems","display_name":"Masked Frequency Modeling for Improving Packet Loss Concealment in Speech Transmission Systems","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764852","doi":"https://doi.org/10.1109/waspaa58266.2023.10248056"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5034929587","display_name":"Da-Hee Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Da-Hee Yang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770748","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0002-2063-5551"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghyun Kim","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea,04763","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/pesq","display_name":"PESQ","score":0.9298660755157471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250442743301392},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.7012511491775513},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.628241240978241},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5529072880744934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5060531497001648},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4658582806587219},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.46294012665748596},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43085557222366333},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4091770052909851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37738513946533203},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1831434965133667},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14896804094314575},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13027602434158325}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9298660755157471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250442743301392},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.7012511491775513},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.628241240978241},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5529072880744934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5060531497001648},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4658582806587219},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.46294012665748596},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43085557222366333},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4091770052909851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37738513946533203},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1831434965133667},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14896804094314575},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13027602434158325},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1503368489","https://openalex.org/W1522301498","https://openalex.org/W1943463263","https://openalex.org/W2137431935","https://openalex.org/W2137539246","https://openalex.org/W2141998673","https://openalex.org/W2146889948","https://openalex.org/W2243752967","https://openalex.org/W2760103357","https://openalex.org/W2766219058","https://openalex.org/W2799789537","https://openalex.org/W2962780374","https://openalex.org/W3015338123","https://openalex.org/W3160450938","https://openalex.org/W3207100935","https://openalex.org/W4205169642","https://openalex.org/W4296069126","https://openalex.org/W4296069296","https://openalex.org/W4297841420","https://openalex.org/W4320013820","https://openalex.org/W4372260323","https://openalex.org/W4375868986","https://openalex.org/W6630152218","https://openalex.org/W6631190155","https://openalex.org/W6638749077"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Packet":[0],"loss":[1],"concealment":[2],"(PLC)":[3],"is":[4],"crucial":[5],"for":[6,44,79,160,170,181],"enhancing":[7],"the":[8,19,26,52,93,108,122,130,134,174],"quality":[9,145,157],"and":[10,143,152,158,177],"intelligibility":[11,159],"of":[12,22,28,140],"speech":[13,161],"processing":[14],"over":[15],"networks":[16],"by":[17,96,116],"ensuring":[18],"accurate":[20],"transmission":[21,162],"data,":[23],"even":[24],"in":[25,39,51,138,173,184],"presence":[27],"packet":[29],"loss.":[30],"In":[31,71,98],"recent":[32],"years,":[33],"significant":[34],"advancements":[35],"have":[36,60],"been":[37,61],"made":[38],"deep":[40],"neural":[41],"network":[42],"approaches":[43],"PLC":[45,58,81,109,136,175],"systems,":[46],"contributing":[47],"to":[48,68,91,107,111],"substantial":[49],"improvements":[50],"field.":[53],"However,":[54],"despite":[55],"these":[56],"advancements,":[57],"systems":[59,82],"biased":[62],"toward":[63],"reconstructing":[64],"lost":[65],"packets,":[66],"leading":[67],"overestimation":[69],"problems.":[70],"this":[72],"study,":[73],"we":[74,100],"propose":[75],"a":[76,88,102,167],"novel":[77],"approach":[78,132],"training":[80],"using":[83],"masked":[84],"frequency":[85,172],"modeling":[86,171],"as":[87],"pre-training":[89],"method":[90,137],"reduce":[92],"artifacts":[94],"generated":[95],"overestimation.":[97],"addition,":[99],"apply":[101],"feature-wise":[103],"linear":[104],"modulation":[105],"layer":[106],"model":[110],"capture":[112],"more":[113],"fine-grained":[114],"features":[115,120],"combining":[117],"previous":[118],"output":[119],"with":[121],"reconstructed":[123],"features.":[124],"The":[125],"experimental":[126],"results":[127],"demonstrate":[128],"that":[129],"proposed":[131],"outperforms":[133],"baseline":[135],"terms":[139],"both":[141],"objective":[142],"subjective":[144],"metrics,":[146],"including":[147],"PLCMOS,":[148],"PESQ,":[149],"STOI,":[150],"LSD,":[151],"WER,":[153],"thus":[154],"providing":[155],"better":[156],"systems.":[163],"This":[164],"study":[165],"presents":[166],"new":[168],"direction":[169],"algorithm":[176],"indicates":[178],"its":[179],"potential":[180],"practical":[182],"applications":[183],"real-world":[185],"scenarios.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}