{"id":"https://openalex.org/W4372260233","doi":"https://doi.org/10.1109/icassp49357.2023.10096362","title":"The NPU-Elevoc Personalized Speech Enhancement System for Icassp2023 DNS Challenge","display_name":"The NPU-Elevoc Personalized Speech Enhancement System for Icassp2023 DNS Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260233","doi":"https://doi.org/10.1109/icassp49357.2023.10096362"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096362","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096362","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/A5001664777","display_name":"Xiaopeng Yan","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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaopeng Yan","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Langauge Processing Group,Xi&#x2019;an,China","Elevoc, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Langauge Processing Group,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Elevoc, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037327543","display_name":"Yindi Yang","orcid":"https://orcid.org/0000-0002-7864-0281"},"institutions":[{"id":"https://openalex.org/I28174512","display_name":"Elekta (Switzerland)","ror":"https://ror.org/00212dq27","country_code":"CH","type":"company","lineage":["https://openalex.org/I28174512","https://openalex.org/I4210123750"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yindi Yang","raw_affiliation_strings":["Elevoc,Shenzhen,China","Elevoc, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Elevoc,Shenzhen,China","institution_ids":["https://openalex.org/I28174512"]},{"raw_affiliation_string":"Elevoc, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103078809","display_name":"Zhihao Guo","orcid":"https://orcid.org/0009-0009-5349-2081"},"institutions":[{"id":"https://openalex.org/I28174512","display_name":"Elekta (Switzerland)","ror":"https://ror.org/00212dq27","country_code":"CH","type":"company","lineage":["https://openalex.org/I28174512","https://openalex.org/I4210123750"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zhihao Guo","raw_affiliation_strings":["Elevoc,Shenzhen,China","Elevoc, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Elevoc,Shenzhen,China","institution_ids":["https://openalex.org/I28174512"]},{"raw_affiliation_string":"Elevoc, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064781749","display_name":"Liangliang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I28174512","display_name":"Elekta (Switzerland)","ror":"https://ror.org/00212dq27","country_code":"CH","type":"company","lineage":["https://openalex.org/I28174512","https://openalex.org/I4210123750"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Liangliang Peng","raw_affiliation_strings":["Elevoc,Shenzhen,China","Elevoc, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Elevoc,Shenzhen,China","institution_ids":["https://openalex.org/I28174512"]},{"raw_affiliation_string":"Elevoc, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"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":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Langauge Processing Group,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Langauge Processing Group,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001664777"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69988108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9998999834060669,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.6840230822563171},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.6521605253219604},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6409695148468018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5833398699760437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5043371915817261},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42597946524620056},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11818936467170715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840230822563171},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6521605253219604},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6409695148468018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5833398699760437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5043371915817261},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42597946524620056},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11818936467170715}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096362","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096362","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","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3207551191","https://openalex.org/W4224919629","https://openalex.org/W4312120895","https://openalex.org/W4319862644","https://openalex.org/W4372265824","https://openalex.org/W4372340947","https://openalex.org/W6846167707","https://openalex.org/W6847037835"],"related_works":["https://openalex.org/W2992516105","https://openalex.org/W2360883279","https://openalex.org/W2055709700","https://openalex.org/W3120899676","https://openalex.org/W3210635025","https://openalex.org/W2560284304","https://openalex.org/W2368779261","https://openalex.org/W2039534605","https://openalex.org/W1506576323","https://openalex.org/W2778699561"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3,29,57],"NPU-Elevoc":[4],"personalized":[5],"speech":[6],"enhancement":[7],"system":[8,30,58],"(NAPSE)":[9],"for":[10,35,61],"the":[11,22,40,53,62,66,75],"5th":[12],"Deep":[13],"Noise":[14],"Suppression":[15],"Challenge[1]":[16],"at":[17],"ICASSP":[18],"2023.":[19],"Based":[20],"on":[21],"superior":[23],"two-stage":[24],"model":[25,41],"TEA-PSE":[26],"2.0":[27],"[2],":[28],"particularly":[31],"explores":[32],"better":[33],"strategy":[34],"speaker":[36],"embedding":[37],"fusion,":[38],"optimizes":[39],"training":[42,47],"pipeline,":[43],"and":[44,48,71],"leverages":[45],"adversarial":[46],"multi-scale":[49],"loss.":[50],"According":[51],"to":[52],"results<sup":[54],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">12</sup>,":[56],"is":[59],"tied":[60],"1st":[63],"place":[64],"in":[65,74],"headset":[67],"track":[68,77],"(track":[69,78],"1)":[70],"ranked":[72],"2nd":[73],"speakerphone":[76],"2).":[79]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
