{"id":"https://openalex.org/W4372346771","doi":"https://doi.org/10.1109/icassp49357.2023.10096838","title":"TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 Dns-Challenge","display_name":"TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 Dns-Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346771","doi":"https://doi.org/10.1109/icassp49357.2023.10096838"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096838","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/A5015448985","display_name":"Yukai Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"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":"Yukai Ju","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xi'an, China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450139","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-7201-1989"},"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":"Jun Chen","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630316","display_name":"Shimin Zhang","orcid":"https://orcid.org/0009-0004-4344-5218"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","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 Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4474,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90958608,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.6928961277008057},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6168823838233948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5823168158531189},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4780160188674927},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.45289745926856995},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42367759346961975},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41284289956092834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3194899559020996},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22398579120635986},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18532076478004456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928961277008057},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6168823838233948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5823168158531189},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4780160188674927},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.45289745926856995},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42367759346961975},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41284289956092834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3194899559020996},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22398579120635986},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18532076478004456},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096838","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":[{"score":0.6299999952316284,"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":5,"referenced_works":["https://openalex.org/W2117678320","https://openalex.org/W3015338123","https://openalex.org/W4224919629","https://openalex.org/W4225905067","https://openalex.org/W4319862644"],"related_works":["https://openalex.org/W2789518417","https://openalex.org/W2566545183","https://openalex.org/W2499449816","https://openalex.org/W2059085722","https://openalex.org/W4213217485","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,8,48,69,73,83,89,93],"Unbeatable":[4],"Team\u2019s":[5],"submission":[6],"to":[7,22,42,55,66,87,92],"ICASSP":[9,102],"2023":[10,103],"Deep":[11],"Noise":[12],"Suppression":[13],"(DNS)":[14],"Challenge.":[15],"We":[16],"expand":[17],"our":[18],"previous":[19],"work,":[20],"TEA-PSE,":[21],"its":[23],"upgraded":[24],"version":[25],"\u2013":[26],"TEA-PSE":[27,30,96],"3.0.":[28],"Specifically,":[29],"3.0":[31,97],"incorporates":[32],"a":[33],"residual":[34],"LSTM":[35],"after":[36],"squeezed":[37],"temporal":[38],"convolution":[39],"network":[40],"(S-TCN)":[41],"enhance":[43],"sequence":[44],"modeling":[45],"capabilities.":[46],"Additionally,":[47],"local-global":[49],"representation":[50],"(LGR)":[51],"structure":[52],"is":[53,64],"introduced":[54],"boost":[56],"speaker":[57],"information":[58],"extraction,":[59],"and":[60,107],"multi-STFT":[61],"resolution":[62],"loss":[63],"used":[65],"effectively":[67],"capture":[68],"time-frequency":[70],"characteristics":[71],"of":[72],"speech":[74],"signals.":[75],"Moreover,":[76],"retraining":[77],"methods":[78],"are":[79],"employed":[80],"based":[81],"on":[82],"freeze":[84],"training":[85],"strategy":[86],"fine-tune":[88],"system.":[90],"According":[91],"official":[94],"results,":[95],"ranks":[98],"1st":[99],"in":[100],"both":[101],"DNS-Challenge":[104],"track":[105,108],"1":[106],"2.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}