{"id":"https://openalex.org/W4319781551","doi":"https://doi.org/10.1109/iscslp57327.2022.10037896","title":"Shuffle is What You Need","display_name":"Shuffle is What You Need","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319781551","doi":"https://doi.org/10.1109/iscslp57327.2022.10037896"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101868991","display_name":"Lin Wan","orcid":"https://orcid.org/0000-0002-9320-3725"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wan Lin","raw_affiliation_strings":["Tsinghua University,CSLT, BNRist","CSLT, BNRist, Tsinghua University","Shen Zhen University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,CSLT, BNRist","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"CSLT, BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shen Zhen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744768","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0002-5546-8060"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Post Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Post Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Tsinghua University,CSLT, BNRist","CSLT, BNRist, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,CSLT, BNRist","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"CSLT, BNRist, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101868991"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3116,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54244775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.9915000200271606,"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/utterance","display_name":"Utterance","score":0.7572026252746582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7226954102516174},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.7199819684028625},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.6782923936843872},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6177126169204712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5728931427001953},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5715148448944092},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5672826170921326},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5530402064323425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44316524267196655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3893798589706421},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1943528950214386}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7572026252746582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226954102516174},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7199819684028625},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.6782923936843872},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6177126169204712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728931427001953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5715148448944092},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5672826170921326},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5530402064323425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44316524267196655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3893798589706421},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1943528950214386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W2046056978","https://openalex.org/W2096733369","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2612434969","https://openalex.org/W2802973008","https://openalex.org/W2890964092","https://openalex.org/W2953327099","https://openalex.org/W2962832278","https://openalex.org/W2963181813","https://openalex.org/W2963371159","https://openalex.org/W2972705840","https://openalex.org/W2972894903","https://openalex.org/W2973049979","https://openalex.org/W2981087920","https://openalex.org/W3015503328","https://openalex.org/W3015598461","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3160397447","https://openalex.org/W3198533616","https://openalex.org/W3209059054","https://openalex.org/W4206908380","https://openalex.org/W4221145109","https://openalex.org/W4297808394","https://openalex.org/W6737575990","https://openalex.org/W6774314701","https://openalex.org/W6779997284","https://openalex.org/W6781368565","https://openalex.org/W6810007534","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W4377131110","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4388857216","https://openalex.org/W2046590706","https://openalex.org/W4390419005","https://openalex.org/W2949444602","https://openalex.org/W1587991081","https://openalex.org/W2386184744"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,21,77],"gains":[2],"extensive":[3],"attention":[4],"in":[5,28,55,71,81,138,154],"speaker":[6,18,72],"recognition,":[7],"partly":[8],"due":[9,74],"to":[10,67,75,125],"the":[11,24,38,51,56,61,76,100,103,110,115,129,135,139,144,152,166],"difficulty":[12],"of":[13,78,102],"collecting":[14],"data":[15],"with":[16],"large-scale":[17],"labels.":[19],"Contrastive":[20],"is":[22],"among":[23],"most":[25],"popular":[26],"approaches":[27],"this":[29,85],"setting,":[30],"where":[31],"similar":[32],"pairs":[33,43,97],"(positive)":[34],"are":[35,45],"sampled":[36,46],"from":[37,47],"same":[39],"utterance":[40],"while":[41],"dissimilar":[42],"(negative)":[44],"different":[48],"utterances.":[49],"Despite":[50],"promising":[52],"results":[53,108],"reported":[54],"literature,":[57],"we":[58,87],"argue":[59],"that":[60,114],"random":[62,126,167],"sampling":[63,168],"approach":[64,117,132],"may":[65],"lead":[66],"unideal":[68],"content":[69,79,137],"residual":[70],"embeddings,":[73],"dependency":[80],"positive":[82,96],"pairs.":[83],"In":[84],"paper,":[86],"investigate":[88],"a":[89],"novel":[90],"frame":[91,130],"shuffle":[92,131],"approach,":[93],"which":[94,142],"constructs":[95],"by":[98],"shuffling":[99],"frames":[101],"anchor":[104],"segment.":[105],"Our":[106],"experimental":[107],"on":[109],"VCTK":[111],"dataset":[112],"showed":[113],"new":[116],"can":[118],"obtain":[119],"comparable":[120],"or":[121],"better":[122],"performance":[123,163],"compared":[124],"sampling.":[127],"Moreover,":[128],"fully":[133],"corrupts":[134],"linguistic":[136],"training":[140],"data,":[141],"enforces":[143],"learned":[145],"model":[146],"being":[147],"language":[148],"independent.":[149],"We":[150],"tested":[151],"hypothesis":[153],"both":[155],"multi-lingual":[156],"and":[157,160],"cross-lingual":[158],"scenarios":[159],"observed":[161],"remarkable":[162],"improvement":[164],"over":[165],"baseline.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}