{"id":"https://openalex.org/W3015306128","doi":"https://doi.org/10.1109/icassp40776.2020.9054311","title":"Speaker-Aware Target Speaker Enhancement by Jointly Learning with Speaker Embedding Extraction","display_name":"Speaker-Aware Target Speaker Enhancement by Jointly Learning with Speaker Embedding Extraction","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015306128","doi":"https://doi.org/10.1109/icassp40776.2020.9054311","mag":"3015306128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5110930567","display_name":"Xuan Ji","orcid":"https://orcid.org/0009-0008-1913-5219"},"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":true,"raw_author_name":"Xuan Ji","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005304261","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-3851-2357"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"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":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, 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/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yu","raw_affiliation_strings":["Tencent IEG, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent IEG, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455531","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0005-6402-3855"},"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":"Xiaoyu Liu","raw_affiliation_strings":["Tencent IEG, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent IEG, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5110930567"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":3.9624,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94491692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7294","last_page":"7298"},"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":0.9987000226974487,"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":0.9965000152587891,"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":0.7888347506523132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7176915407180786},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7000638246536255},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6765564680099487},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6582332253456116},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5931136012077332},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4393007457256317},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4307458996772766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.407236248254776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32713404297828674},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15173983573913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888347506523132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7176915407180786},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7000638246536255},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6765564680099487},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6582332253456116},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5931136012077332},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4393007457256317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4307458996772766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.407236248254776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32713404297828674},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15173983573913574},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/icassp40776.2020.9054311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1991139021","https://openalex.org/W2096733369","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2401812832","https://openalex.org/W2558649592","https://openalex.org/W2584329820","https://openalex.org/W2734774145","https://openalex.org/W2747238065","https://openalex.org/W2755891984","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2889017397","https://openalex.org/W2889048668","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2892365986","https://openalex.org/W2900893004","https://openalex.org/W2938646939","https://openalex.org/W2939634425","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2964238697","https://openalex.org/W2972425344","https://openalex.org/W2972802573","https://openalex.org/W2972961496","https://openalex.org/W2973062255","https://openalex.org/W3008400075","https://openalex.org/W3099206234","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6631362777","https://openalex.org/W6688843265","https://openalex.org/W6712730384","https://openalex.org/W6732884072","https://openalex.org/W6744261651","https://openalex.org/W6754473786","https://openalex.org/W6754743415","https://openalex.org/W6755462816"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"speech":[3,15,70,85,94,102],"separation":[4],"approaches":[5],"have":[6],"received":[7],"great":[8],"interest,":[9],"among":[10],"which":[11,42],"the":[12,45,63,93,99],"recent":[13],"speaker-aware":[14,101],"enhancement":[16,95,103],"methods":[17],"are":[18],"promising":[19],"for":[20,67],"solving":[21],"difficulties":[22],"such":[23],"as":[24],"arbitrary":[25],"source":[26],"permutation":[27],"and":[28,51,79],"unknown":[29],"number":[30],"of":[31,83],"sources.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"propose":[37],"a":[38],"novel":[39],"training":[40],"framework":[41],"jointly":[43],"learns":[44,62],"speaker-conditioned":[46],"target":[47,69],"speaker":[48,54,65],"extraction":[49],"model":[50,60],"its":[52],"associated":[53],"embedding":[55,66],"model.":[56],"The":[57],"resulting":[58],"unified":[59],"directly":[61],"appropriate":[64],"improved":[68],"enhancement.":[71],"We":[72],"demonstrate,":[73],"on":[74],"our":[75,88],"large":[76],"simulated":[77],"noisy":[78],"far-field":[80],"evaluation":[81],"sets":[82],"overlapped":[84],"signals,":[86],"that":[87],"proposed":[89],"approach":[90],"significantly":[91],"improves":[92],"performance":[96],"compared":[97],"to":[98],"baseline":[100],"models.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}