{"id":"https://openalex.org/W4372262790","doi":"https://doi.org/10.1109/icassp49357.2023.10097210","title":"TSpeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge","display_name":"TSpeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262790","doi":"https://doi.org/10.1109/icassp49357.2023.10097210"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097210","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/A5084353066","display_name":"Jianwei Yu","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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hangting Chen","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038895203","display_name":"Rongzhi Gu","orcid":"https://orcid.org/0000-0003-1861-9170"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Rongzhi Gu","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400668","display_name":"Weihua Li","orcid":"https://orcid.org/0000-0002-6190-8421"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Weihua Li","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab","Tencent AI Lab, Audio and Speech Signal Processing Oteam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Tencent AI Lab, Audio and Speech Signal Processing Oteam","institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9876999855041504,"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/headset","display_name":"Headset","score":0.6875556111335754},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6551964282989502},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5916861295700073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5823555588722229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5820215344429016},{"id":"https://openalex.org/keywords/raspberry-pi","display_name":"Raspberry pi","score":0.5778313279151917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222338438034058},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47457340359687805},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4328468143939972},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4178731441497803},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4152947962284088},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15578439831733704},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14468088746070862},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.11340516805648804},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.09714850783348083},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09609508514404297},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09197714924812317},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08313450217247009}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.6875556111335754},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6551964282989502},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5916861295700073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823555588722229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5820215344429016},{"id":"https://openalex.org/C2985745059","wikidata":"https://www.wikidata.org/wiki/Q245","display_name":"Raspberry pi","level":3,"score":0.5778313279151917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222338438034058},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47457340359687805},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4328468143939972},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4178731441497803},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4152947962284088},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15578439831733704},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14468088746070862},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.11340516805648804},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.09714850783348083},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09609508514404297},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09197714924812317},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08313450217247009},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icassp49357.2023.10097210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097210","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/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3197273793","https://openalex.org/W4224919629","https://openalex.org/W4283458492","https://openalex.org/W4375928773","https://openalex.org/W6839093550","https://openalex.org/W6845155585"],"related_works":["https://openalex.org/W2549567669","https://openalex.org/W104838418","https://openalex.org/W1532889363","https://openalex.org/W4292416459","https://openalex.org/W2394331374","https://openalex.org/W4225253169","https://openalex.org/W2626842453","https://openalex.org/W2946426818","https://openalex.org/W4321180712","https://openalex.org/W2361580522"],"abstract_inverted_index":{"This":[0],"report":[1],"presents":[2],"the":[3,14,33,57,67,78],"development":[4],"of":[5,35],"Tencent":[6],"AI":[7],"Lab\u2019s":[8],"personalized":[9],"speech":[10],"enhancement":[11],"system":[12,55,59],"for":[13],"2023":[15],"ICASSP":[16],"Signal":[17],"Processing":[18],"Grand":[19],"Challenge":[20],"\u2013":[21],"deep":[22],"noise":[23],"suppression":[24],"(DNS)":[25],"challenge":[26],"<sup":[27,80],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,81],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[29],",":[30],"which":[31],"includes":[32],"use":[34],"a":[36,44],"modified":[37],"band-split":[38],"recurrent":[39],"neural":[40],"network":[41],"(BSRNN)":[42],"and":[43,62,70,75],"multi-resolution":[45],"spectrogram":[46],"discriminator":[47],"to":[48],"improve":[49],"perceptual":[50],"quality":[51],"metrics.":[52],"The":[53],"proposed":[54],"outperforms":[56],"baseline":[58],"by":[60],"0.047":[61],"0.036":[63],"final":[64],"scores":[65],"in":[66,83],"headset":[68],"track":[69],"speaker":[71],"phone":[72],"track,":[73],"respectively,":[74],"ranks":[76],"among":[77],"top-3":[79],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[82],"both":[84],"tracks.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}