{"id":"https://openalex.org/W4372263462","doi":"https://doi.org/10.1109/icassp49357.2023.10094845","title":"SSI-Net: A Multi-Stage Speech Signal Improvement System for ICASSP 2023 SSI Challenge","display_name":"SSI-Net: A Multi-Stage Speech Signal Improvement System for ICASSP 2023 SSI Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263462","doi":"https://doi.org/10.1109/icassp49357.2023.10094845"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094845","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094845","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":"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/A5021314526","display_name":"Weixin Zhu","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":"Weixin Zhu","raw_affiliation_strings":["Tencent,Shenzhen,China","Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326031","display_name":"Zilin Wang","orcid":"https://orcid.org/0009-0003-6062-3015"},"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":"Zilin Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"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/A5025480447","display_name":"Jiuxin Lin","orcid":null},"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":"Jiuxin Lin","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"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/A5100654128","display_name":"Chang Zeng","orcid":"https://orcid.org/0000-0002-4882-1823"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chang Zeng","raw_affiliation_strings":["SOKENDAI,Kanagawa,Japan","SOKENDAI, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOKENDAI,Kanagawa,Japan","institution_ids":["https://openalex.org/I4210110163"]},{"raw_affiliation_string":"SOKENDAI, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210110163","https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057697869","display_name":"Tao Yu","orcid":"https://orcid.org/0000-0002-0143-261X"},"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":"Tao Yu","raw_affiliation_strings":["Tencent,Shenzhen,China","Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9983000159263611,"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":0.6658986806869507},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6451467275619507},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6008223295211792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.557295024394989},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5380721688270569},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5055618286132812},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4896264672279358},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43935665488243103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3302015960216522},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1433282494544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658986806869507},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6451467275619507},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6008223295211792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.557295024394989},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5380721688270569},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5055618286132812},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4896264672279358},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43935665488243103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3302015960216522},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1433282494544983},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094845","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094845","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2117678320","https://openalex.org/W2172065531","https://openalex.org/W3092028330","https://openalex.org/W3197095449","https://openalex.org/W3215615641","https://openalex.org/W4224931234","https://openalex.org/W4225905067","https://openalex.org/W4297841545","https://openalex.org/W4392693577","https://openalex.org/W6783867762","https://openalex.org/W6850335419"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W3196343857","https://openalex.org/W2089240210","https://openalex.org/W2139455842","https://openalex.org/W2131486661","https://openalex.org/W4287113595","https://openalex.org/W111365173"],"abstract_inverted_index":{"The":[0,43],"ICASSP":[1,34],"2023":[2,35],"Speech":[3],"Signal":[4],"Improvement":[5],"(SSI)":[6],"Challenge":[7,99],"concentrates":[8],"on":[9,96],"improving":[10],"the":[11,25,33,40,52,60,68,89,93,97,126],"speech":[12,26,65],"signal":[13,27],"quality":[14],"of":[15,114,121],"real-time":[16,41],"communication":[17],"(RTC)":[18],"systems.":[19],"In":[20,92],"this":[21],"paper,":[22],"we":[23,72],"introduce":[24],"improvement":[28],"network":[29,57,80],"(SSI-Net)":[30],"submitted":[31],"to":[32,87],"SSI":[36,98],"Challenge,":[37],"which":[38,123],"satisfies":[39],"condition.":[42],"proposed":[44,104],"SSI-Net":[45,105],"has":[46],"a":[47,74,107,117],"multi-stage":[48],"architecture.":[49],"We":[50],"present":[51],"time-domain":[53],"restoration":[54,62],"generative":[55],"adversarial":[56],"(TRGAN)":[58],"in":[59,129],"first":[61],"stage":[63],"for":[64],"restoration.":[66],"Regarding":[67],"second":[69],"enhancement":[70],"stage,":[71],"employ":[73],"lightweight":[75],"multi-scale":[76],"temporal":[77],"frequency":[78],"convolutional":[79],"with":[81],"axial":[82],"self-attention":[83],"(MTFAA-Net)":[84],"called":[85],"MTFAA-Lite":[86],"enhance":[88],"fullband":[90],"speech.":[91],"subjective":[94],"test":[95,101],"blind":[100],"set,":[102],"our":[103],"yields":[106],"P.835":[108],"overall":[109,119],"mean":[110],"opinion":[111],"score":[112],"(MOS)":[113],"3.190":[115],"and":[116],"P.804":[118],"MOS":[120],"3.178,":[122],"eventually":[124],"takes":[125],"3rd":[127],"place":[128],"tracks":[130],"1&2.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}