{"id":"https://openalex.org/W4224925682","doi":"https://doi.org/10.1109/icassp43922.2022.9746981","title":"Multi-Stage and Multi-Loss Training for Fullband Non-Personalized and Personalized Speech Enhancement","display_name":"Multi-Stage and Multi-Loss Training for Fullband Non-Personalized and Personalized Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925682","doi":"https://doi.org/10.1109/icassp43922.2022.9746981"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746981","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5072495935","display_name":"Lianwu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lianwu Chen","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437205","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-1533-4340"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023288436","display_name":"Xinlei Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinlei Ren","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034844592","display_name":"Xiguang Zheng","orcid":"https://orcid.org/0000-0003-3103-9090"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiguang Zheng","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374052","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0001-5773-9090"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614103","display_name":"Liang Guo","orcid":"https://orcid.org/0000-0003-3382-9918"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Guo","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544262","display_name":"Bing Yu","orcid":"https://orcid.org/0000-0002-1697-6089"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yu","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5072495935"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.6145,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63823065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9296","last_page":"9300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8203443288803101},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.7327982187271118},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6988485455513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6751900911331177},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.5448529720306396},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4913558065891266},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44396767020225525},{"id":"https://openalex.org/keywords/multi-stage","display_name":"Multi stage","score":0.42270755767822266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4034615159034729},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.36057963967323303},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.10724416375160217},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10468915104866028},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.06346240639686584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203443288803101},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.7327982187271118},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6988485455513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6751900911331177},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.5448529720306396},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4913558065891266},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44396767020225525},{"id":"https://openalex.org/C3017905481","wikidata":"https://www.wikidata.org/wiki/Q1161829","display_name":"Multi stage","level":2,"score":0.42270755767822266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4034615159034729},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.36057963967323303},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.10724416375160217},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10468915104866028},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.06346240639686584},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746981","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2286859569","https://openalex.org/W2758003289","https://openalex.org/W2889442120","https://openalex.org/W2937484199","https://openalex.org/W2963868408","https://openalex.org/W2971417062","https://openalex.org/W2973049979","https://openalex.org/W3016361963","https://openalex.org/W3027008958","https://openalex.org/W3095248373","https://openalex.org/W3096408984","https://openalex.org/W3097966334","https://openalex.org/W3103434036","https://openalex.org/W3160085755","https://openalex.org/W3194338569","https://openalex.org/W3194687854","https://openalex.org/W3196888558","https://openalex.org/W3197260772","https://openalex.org/W3197284240","https://openalex.org/W3197478142","https://openalex.org/W3216004336","https://openalex.org/W4224928157","https://openalex.org/W4225905067","https://openalex.org/W6777776875","https://openalex.org/W6794736452","https://openalex.org/W6804608017"],"related_works":["https://openalex.org/W1534361175","https://openalex.org/W1578591928","https://openalex.org/W2158843472","https://openalex.org/W1582333646","https://openalex.org/W1519690927","https://openalex.org/W2151333624","https://openalex.org/W160393331","https://openalex.org/W2101490115","https://openalex.org/W106981560","https://openalex.org/W2140646420"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"wideband":[2,17],"(16kHz)":[3],"speech":[4,23,29,35],"enhancement":[5,24],"approaches":[6],"have":[7],"surpassed":[8],"traditional":[9],"methods.":[10],"This":[11],"work":[12],"further":[13],"extends":[14],"the":[15,40,56,70],"existing":[16],"systems":[18],"to":[19],"enable":[20],"full-band":[21],"(48kHz)":[22],"while":[25],"simultaneously":[26],"ensuring":[27],"automatic":[28],"recognition":[30],"compatibility":[31],"and":[32,50,69],"optionally,":[33],"personalized":[34],"enhancement.":[36],"As":[37],"shown":[38],"in":[39],"evaluation":[41],"results,":[42],"this":[43],"is":[44],"achieved":[45],"by":[46,64],"employing":[47],"a":[48,65],"multi-stage":[49],"multi-loss":[51],"training":[52],"architecture":[53],"that":[54],"incorporates":[55],"recently":[57],"proposed":[58],"two-step":[59],"structure,":[60],"ASR":[61,67],"loss":[62],"produced":[63],"back-end":[66],"encoder,":[68],"speaker":[71],"extraction":[72],"network.":[73]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}