{"id":"https://openalex.org/W4375869170","doi":"https://doi.org/10.1109/icassp49357.2023.10095557","title":"Gesper: A Unified Framework for General Speech Restoration","display_name":"Gesper: A Unified Framework for General Speech Restoration","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869170","doi":"https://doi.org/10.1109/icassp49357.2023.10095557"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100450139","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-7201-1989"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Chen","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020510777","display_name":"Yupeng Shi","orcid":"https://orcid.org/0009-0001-8898-6278"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Shi","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679522","display_name":"Wenzhe Liu","orcid":"https://orcid.org/0000-0002-0827-6883"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Liu","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072851763","display_name":"Wei Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yannan Wang","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078353046","display_name":"Shidong Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shidong Shang","raw_affiliation_strings":["Tencent Ethereal Audio Lab,Tencent,China","Tencent Ethereal Audio Lab, Tencent, China"],"affiliations":[{"raw_affiliation_string":"Tencent Ethereal Audio Lab,Tencent,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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/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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100450139"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.2743,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88737552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.6924403309822083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4754978120326996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34136611223220825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924403309822083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4754978120326996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34136611223220825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Sustainable cities and communities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3092028330","https://openalex.org/W3197095449","https://openalex.org/W4221155601","https://openalex.org/W4225905067","https://openalex.org/W4296068992","https://openalex.org/W4312570973","https://openalex.org/W4392693577","https://openalex.org/W6783867762","https://openalex.org/W6850335419"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,22],"paper":[1],"describes":[2],"the":[3,14,32,54,59,67,77,86,92],"legends-tencent":[4],"team\u2019s":[5],"real-time":[6,93],"General":[7],"Speech":[8,17],"Restoration":[9],"(Gesper)":[10],"system":[11,25],"submitted":[12],"to":[13],"ICASSP":[15,82],"2023":[16,83],"Signal":[18],"Improvement":[19],"(SSI)":[20],"Challenge.":[21],"newly":[23],"proposed":[24,87],"is":[26,35,70],"a":[27,45],"two-stage":[28],"architecture,":[29],"in":[30,110],"which":[31,90],"speech":[33,41,55],"restoration":[34,56],"performed,":[36],"and":[37,65,103,114],"then":[38],"followed":[39],"by":[40],"enhancement.":[42],"We":[43],"propose":[44],"complex":[46],"spectral":[47],"mapping-based":[48],"generative":[49],"adversarial":[50],"network":[51],"(CSM-GAN)":[52],"as":[53],"module":[57,69],"for":[58],"first":[60],"time.":[61],"For":[62],"noise":[63],"suppression":[64],"dereverberation,":[66],"enhancement":[68],"presented":[71],"with":[72],"fullband-wideband":[73],"parallel":[74],"processing.":[75],"On":[76],"blind":[78],"test":[79],"set":[80],"of":[81],"SSI":[84],"Challenge,":[85],"Gesper":[88],"system,":[89],"satisfies":[91],"condition,":[94],"achieves":[95],"3.27":[96],"P.804":[97],"overall":[98,106],"mean":[99],"opinion":[100],"score":[101],"(MOS)":[102],"3.35":[104],"P.835":[105],"MOS,":[107],"ranked":[108],"1st":[109],"both":[111],"track":[112,115],"1":[113],"2.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}