{"id":"https://openalex.org/W4372340947","doi":"https://doi.org/10.1109/icassp49357.2023.10096626","title":"Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit","display_name":"Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372340947","doi":"https://doi.org/10.1109/icassp49357.2023.10096626"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096626","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/A5101406825","display_name":"Hongji Wang","orcid":"https://orcid.org/0000-0002-8834-1592"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":"Hongji Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","WeNet Open Source Community","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027514862","display_name":"Chengdong Liang","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"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chengdong Liang","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","NVIDIA, Santa Clara, USA","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":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]},{"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/A5100328340","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0003-1523-9631"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen","WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449716","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-7164-5127"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["Horizon Robotics,Beijing,China","WeNet Open Source Community","Horizon Robotics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055220405","display_name":"Xu Xiang","orcid":"https://orcid.org/0000-0003-2530-9023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Xiang","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007685018","display_name":"Yanlei Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanlei Deng","raw_affiliation_strings":["NVIDIA,Santa Clara,USA","NVIDIA, Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"CSE Dept, MoE Key Lab of AI, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.79,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.99440959,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.824519157409668},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8119620084762573},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.79313725233078},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6619845032691956},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5404987335205078},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5281424522399902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4553012549877167},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4314899146556854},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.412769615650177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3181000351905823},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.18237417936325073},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17307966947555542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824519157409668},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8119620084762573},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.79313725233078},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6619845032691956},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5404987335205078},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5281424522399902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4553012549877167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4314899146556854},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.412769615650177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3181000351905823},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.18237417936325073},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17307966947555542},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096626","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2046056978","https://openalex.org/W2219249508","https://openalex.org/W2271840356","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W2981087920","https://openalex.org/W2991951409","https://openalex.org/W3006889321","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3038871978","https://openalex.org/W3094374485","https://openalex.org/W3103152812","https://openalex.org/W3111481301","https://openalex.org/W3163421828","https://openalex.org/W3167533889","https://openalex.org/W3197478142","https://openalex.org/W3198698812","https://openalex.org/W4206908380","https://openalex.org/W4221167533","https://openalex.org/W4221167707","https://openalex.org/W4283458492","https://openalex.org/W4288091954","https://openalex.org/W4289750118","https://openalex.org/W4295312788","https://openalex.org/W6603616073","https://openalex.org/W6631362777","https://openalex.org/W6694517276","https://openalex.org/W6743579824","https://openalex.org/W6748010250","https://openalex.org/W6753575415","https://openalex.org/W6766978945","https://openalex.org/W6769178842","https://openalex.org/W6771538394","https://openalex.org/W6787439801","https://openalex.org/W6801723603","https://openalex.org/W6809668307","https://openalex.org/W6839093550"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Speaker":[0],"modeling":[1,17],"is":[2,19,86,106],"essential":[3],"for":[4,101],"many":[5],"related":[6,91],"tasks,":[7],"such":[8,82],"as":[9,83],"speaker":[10,13,24,34,48,73,84],"recognition":[11],"and":[12,31,53,95],"diarization.":[14],"The":[15,76,104],"dominant":[16],"approach":[18],"fixed-dimensional":[20],"vector":[21],"representation,":[22],"i.e.,":[23],"embedding.":[25],"This":[26],"paper":[27],"introduces":[28],"a":[29],"research":[30],"production":[32],"oriented":[33],"embedding":[35,49],"learning":[36],"toolkit,":[37],"Wespeaker.":[38],"Wespeaker":[39],"contains":[40],"the":[41,68,90],"implementation":[42],"of":[43],"scalable":[44],"data":[45],"management,":[46],"state-of-the-art":[47],"models,":[50],"loss":[51],"functions,":[52],"scoring":[54],"back-ends,":[55],"with":[56],"highly":[57],"competitive":[58],"results":[59],"achieved":[60],"by":[61],"structured":[62],"recipes":[63],"which":[64],"were":[65],"adopted":[66],"in":[67,71,89],"winning":[69],"systems":[70],"several":[72],"verification":[74],"challenges.":[75],"application":[77],"to":[78],"other":[79],"downstream":[80],"tasks":[81],"diarization":[85],"also":[87],"exhibited":[88],"recipe.":[92],"Moreover,":[93],"CPU-":[94],"GPU-compatible":[96],"deployment":[97],"codes":[98],"are":[99],"integrated":[100],"production-oriented":[102],"development.":[103],"toolkit":[105],"publicly":[107],"available":[108],"at":[109],"https://github.com/wenet-e2e/wespeaker.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":9}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}
