{"id":"https://openalex.org/W4292773487","doi":"https://doi.org/10.1145/3548636.3548644","title":"Wav2sv: End-to-end Speaker Embeddings Learning from Raw Waveforms based on Metric Learning for Speaker Verification","display_name":"Wav2sv: End-to-end Speaker Embeddings Learning from Raw Waveforms based on Metric Learning for Speaker Verification","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4292773487","doi":"https://doi.org/10.1145/3548636.3548644"},"language":"en","primary_location":{"id":"doi:10.1145/3548636.3548644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548636.3548644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Information Technology and Computer Communications (ITCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101688221","display_name":"Zhiqing Chen","orcid":"https://orcid.org/0000-0002-4905-884X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqing Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101996132","display_name":"Yifan Pan","orcid":"https://orcid.org/0000-0002-7324-4036"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Pan","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595763","display_name":"Haoran Zhang","orcid":"https://orcid.org/0009-0001-5901-9369"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056706680","display_name":"Yuesheng Zhu","orcid":"https://orcid.org/0000-0003-2524-6800"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuesheng Zhu","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"58"},"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":0.9986000061035156,"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/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":0.7902455925941467},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6117851734161377},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5811013579368591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5667078495025635},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5604875683784485},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5415762662887573},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5227434635162354},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4946107566356659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47112178802490234},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45914411544799805},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42885324358940125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4006463289260864},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07718142867088318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902455925941467},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6117851734161377},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5811013579368591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5667078495025635},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5604875683784485},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5415762662887573},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5227434635162354},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4946107566356659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47112178802490234},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45914411544799805},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42885324358940125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4006463289260864},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07718142867088318},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3548636.3548644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548636.3548644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Information Technology and Computer Communications (ITCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2150769028","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2770454110","https://openalex.org/W2794506738","https://openalex.org/W2890704021","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2939710050","https://openalex.org/W2964052309","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3029286132","https://openalex.org/W3096084197","https://openalex.org/W3114586009","https://openalex.org/W3197940657","https://openalex.org/W4236377898"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"With":[0],"the":[1,7,12,38,46,100,105,120,142,155,161],"application":[2],"of":[3,9,14,83,148,164],"deep":[4],"learning":[5,111,131],"in":[6,63],"field":[8],"speaker":[10,15,47,51,57,106,123,133,166],"recognition,":[11],"performance":[13],"recognition":[16],"systems":[17,34],"has":[18],"been":[19],"greatly":[20],"improved.":[21],"However,":[22],"most":[23,121],"current":[24],"work":[25,159],"still":[26],"relies":[27],"on":[28,129,138],"handcrafted":[29],"features,":[30],"existing":[31],"raw":[32,126,169],"waveform-based":[33],"fail":[35],"to":[36,55,154],"utilize":[37],"multi-scale":[39],"feature":[40,89],"and":[41,92,103],"multi-level":[42],"information":[43],"efficiently.":[44],"Besides,":[45],"embedding":[48,107,124],"generated":[49],"by":[50],"identification":[52],"is":[53,151],"used":[54],"complete":[56],"verification":[58],"through":[59],"similarity":[60],"discrimination,":[61],"resulting":[62],"a":[64,81,88,109],"domain":[65],"mismatch":[66],"problem.":[67],"To":[68],"address":[69],"these":[70],"problems,":[71],"we":[72],"propose":[73],"an":[74,146],"end-to-end":[75,115],"system":[76,116],"called":[77],"Wav2sv,":[78],"which":[79,150],"uses":[80],"stack":[82],"strided":[84],"convolution":[85],"layers":[86],"as":[87,99],"encoder,":[90],"SE-Res2Blocks":[91],"dense":[93],"connection":[94],"between":[95],"each":[96],"frame":[97,101],"layer":[98],"aggregator;":[102],"obtain":[104],"with":[108],"metric":[110,130],"objective.":[112],"This":[113],"new":[114],"can":[117],"automatically":[118],"learn":[119],"suitable":[122],"from":[125,168],"waveform":[127],"based":[128],"for":[132],"verification.":[134],"Our":[135,158],"simulation":[136],"results":[137],"VoxCeleb1":[139],"indicate":[140],"that":[141],"proposed":[143],"approach":[144],"achieves":[145],"EER":[147],"4.75%,":[149],"18%":[152],"superior":[153],"Wav2spk":[156],"baseline.":[157],"demonstrates":[160],"great":[162],"potential":[163],"extracting":[165],"embeddings":[167],"waveforms.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}