{"id":"https://openalex.org/W4296916926","doi":"https://doi.org/10.1109/wocc55104.2022.9880598","title":"Large-Scale Multi-Channel Transformer-based Speaker Identification with Knowledge Transfer Using Harmonic-Percussive Source Separation","display_name":"Large-Scale Multi-Channel Transformer-based Speaker Identification with Knowledge Transfer Using Harmonic-Percussive Source Separation","publication_year":2022,"publication_date":"2022-08-11","ids":{"openalex":"https://openalex.org/W4296916926","doi":"https://doi.org/10.1109/wocc55104.2022.9880598"},"language":"en","primary_location":{"id":"doi:10.1109/wocc55104.2022.9880598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc55104.2022.9880598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st Wireless and Optical Communications Conference (WOCC)","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/A5055620193","display_name":"Yuejiao Xie","orcid":null},"institutions":[{"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":true,"raw_author_name":"Yuejiao Xie","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061554949","display_name":"Jingjing Tang","orcid":"https://orcid.org/0000-0003-1318-3566"},"institutions":[{"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":"Jingjing Tang","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058661899","display_name":"Nan Yang","orcid":"https://orcid.org/0000-0002-2012-6861"},"institutions":[{"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":"Nan Yang","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040559125","display_name":"Man-On Pun","orcid":"https://orcid.org/0000-0003-3316-5381"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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":"Man-On Pun","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172","Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055620193"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10559582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7390071153640747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6589468717575073},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5800512433052063},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5223482847213745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4779933989048004},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.419014036655426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3946160078048706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36099863052368164},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3491915464401245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2542269825935364},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15262454748153687},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0984332263469696}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7390071153640747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589468717575073},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5800512433052063},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5223482847213745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4779933989048004},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.419014036655426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3946160078048706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36099863052368164},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3491915464401245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2542269825935364},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15262454748153687},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0984332263469696}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wocc55104.2022.9880598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wocc55104.2022.9880598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 31st Wireless and Optical Communications Conference (WOCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7199178231","display_name":null,"funder_award_id":"2020YFB1807700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W16066432","https://openalex.org/W86526702","https://openalex.org/W2041823554","https://openalex.org/W2117539524","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2726515241","https://openalex.org/W2890223581","https://openalex.org/W4214588794","https://openalex.org/W4385245566","https://openalex.org/W6684191040","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2897924318","https://openalex.org/W2098101267","https://openalex.org/W2138997758","https://openalex.org/W2059119686","https://openalex.org/W2898606530","https://openalex.org/W4289362680"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,39,78,114],"multi-channel":[4,17,41],"transformer-based":[5,115],"speaker":[6,104],"identification":[7,105,146],"scheme":[8,14,126],"using":[9],"transfer":[10],"learning.":[11],"The":[12],"proposed":[13,54,125],"first":[15],"generates":[16],"signals":[18,31,97],"by":[19],"extracting":[20],"the":[21,28,57,63,65,68,73,95,103,121,124,135,151,156],"harmonic":[22,66],"and":[23,51,67],"percussive":[24,69],"acoustic":[25,70],"sources":[26],"from":[27],"given":[29],"voice":[30],"through":[32],"harmonic-percussive":[33],"source":[34,157],"separation":[35],"(HPSS).":[36],"After":[37],"that,":[38],"novel":[40],"transformer":[42,52,74],"based":[43],"network":[44],"composed":[45],"of":[46,139,145],"convolution":[47],"neural":[48],"networks":[49],"(CNNs)":[50],"is":[53,127],"to":[55,82,93,129,150],"fuse":[56],"resulting":[58],"three":[59],"signal":[60,158],"sources,":[61],"namely":[62],"original,":[64],"sources.":[71],"However,":[72],"architecture":[75,116],"generally":[76],"requires":[77],"large":[79],"training":[80],"dataset":[81,138],"achieve":[83,130],"good":[84],"performance.":[85],"To":[86],"cope":[87],"with":[88,120,155],"this":[89],"challenge,":[90],"we":[91],"propose":[92],"convert":[94],"audio":[96],"into":[98,107],"their":[99],"spectrograms":[100],"before":[101],"casting":[102],"problem":[106],"an":[108],"image":[109],"classification":[110],"framework.":[111],"By":[112],"exploiting":[113],"called":[117],"LeViT":[118],"pre-trained":[119],"ImageNet":[122],"dataset,":[123],"shown":[128],"about":[131],"9%":[132],"improvement":[133],"on":[134],"challenging":[136],"VoxCeleb1":[137],"1,":[140],"251":[141],"speakers":[142],"in":[143],"terms":[144],"accuracy":[147],"as":[148],"compared":[149],"conventional":[152],"CNNs":[153],"trained":[154],"only.":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}