{"id":"https://openalex.org/W4401611825","doi":"https://doi.org/10.1109/icasspw62465.2024.10626452","title":"Renet: A Time-Frequency Domain General Speech Restoration Network for Icassp 2024 Speech Signal Improvement Challenge","display_name":"Renet: A Time-Frequency Domain General Speech Restoration Network for Icassp 2024 Speech Signal Improvement Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401611825","doi":"https://doi.org/10.1109/icasspw62465.2024.10626452"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5088554529","display_name":"Fengyuan Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyuan Hao","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572570","display_name":"Huiyong Zhang","orcid":"https://orcid.org/0009-0006-6268-7487"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyong Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015589578","display_name":"Lingling Dai","orcid":"https://orcid.org/0000-0001-5345-5824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingling Dai","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090663707","display_name":"Xiaoxue Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxue Luo","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369719","display_name":"Xiaodong Li","orcid":"https://orcid.org/0000-0003-0346-1526"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Li","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Key Laboratory of Noise and Vibration Research, Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894999861717224,"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":0.9894999861717224,"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":0.983299970626831,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9241999983787537,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6292712688446045},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6013208031654358},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.554012656211853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5510091781616211},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.526443362236023},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4688872992992401},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41769149899482727},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1431334912776947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6292712688446045},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6013208031654358},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.554012656211853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5510091781616211},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.526443362236023},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4688872992992401},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41769149899482727},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1431334912776947},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3096159803","https://openalex.org/W4224133928","https://openalex.org/W4225905067","https://openalex.org/W4372271367","https://openalex.org/W4375869170","https://openalex.org/W4388620484","https://openalex.org/W4392903243","https://openalex.org/W4401610398"],"related_works":["https://openalex.org/W2782295999","https://openalex.org/W2162306796","https://openalex.org/W1970292246","https://openalex.org/W2016162169","https://openalex.org/W4247952185","https://openalex.org/W1895367623","https://openalex.org/W1642462315","https://openalex.org/W2015118744","https://openalex.org/W2005619368","https://openalex.org/W1879092539"],"abstract_inverted_index":{"The":[0],"ICASSP":[1,126],"2024":[2,127],"Speech":[3],"Signal":[4],"Improvement":[5],"(SSI)":[6],"Challenge":[7],"seeks":[8],"to":[9,34,50,68,89],"address":[10],"speech":[11,36,54,93],"quality":[12,94],"degradation":[13],"problems":[14],"in":[15,75,120],"telecommunication":[16],"systems.":[17],"In":[18],"this":[19,21],"context,":[20],"paper":[22],"proposes":[23],"RENet,":[24],"a":[25,43,56,62,81],"time-frequency":[26],"(T-F)":[27],"domain":[28],"method":[29,108,115],"leveraging":[30],"complex":[31],"spectrum":[32],"mapping":[33],"mitigate":[35],"distortions.":[37],"Specifically,":[38],"the":[39,52,76,92,102,106,113,117,121,125],"proposed":[40,107,114],"RENet":[41],"is":[42],"multi-stage":[44],"network.":[45],"First,":[46],"TF-GridGAN":[47],"was":[48,66,87],"designed":[49],"recover":[51],"degraded":[53],"with":[55],"generative":[57],"adversarial":[58],"network":[59,86],"(GAN).":[60],"Second,":[61],"full-band":[63],"enhancement":[64],"module":[65],"introduced":[67],"eliminate":[69],"residual":[70],"noises":[71],"and":[72,112],"artifacts":[73],"existed":[74],"output":[77],"of":[78,105,124],"TF-GridGAN.":[79],"Finally,":[80],"lightweight":[82],"bandwidth":[83],"extension":[84],"(BWE)":[85],"implemented":[88],"further":[90],"improve":[91],"by":[95],"generating":[96],"high-resolution":[97],"speeches.":[98],"Subjective":[99],"results":[100],"confirmed":[101],"competitive":[103],"performance":[104],"under":[109],"various":[110],"distortions,":[111],"ranked":[116],"2nd":[118],"place":[119],"non-real-time":[122],"track":[123],"SSI":[128],"Challenge.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
