{"id":"https://openalex.org/W4372349540","doi":"https://doi.org/10.1109/icassp49357.2023.10096976","title":"Contrastive Speech Mixup for Low-Resource Keyword Spotting","display_name":"Contrastive Speech Mixup for Low-Resource Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349540","doi":"https://doi.org/10.1109/icassp49357.2023.10096976"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096976","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/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["SG","US"],"is_corresponding":true,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866147","display_name":"Ruixi Zhang","orcid":"https://orcid.org/0000-0002-0376-4327"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Ruixi Zhang","raw_affiliation_strings":["Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568886","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-4419-4287"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562097","display_name":"Trung Hieu Nguyen","orcid":"https://orcid.org/0000-0002-2683-253X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trung Hieu Nguyen","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5104217727"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":2.1567,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88589726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9994000196456909,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9459133148193359},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8395094871520996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5271358489990234},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5175149440765381},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4813893139362335},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46484819054603577},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4574858248233795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41815805435180664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35283762216567993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32798564434051514}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9459133148193359},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395094871520996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5271358489990234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5175149440765381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4813893139362335},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46484819054603577},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4574858248233795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41815805435180664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35283762216567993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32798564434051514},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096976","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2407080277","https://openalex.org/W2765407302","https://openalex.org/W2797583228","https://openalex.org/W2910655080","https://openalex.org/W2936774411","https://openalex.org/W2973226577","https://openalex.org/W2992308087","https://openalex.org/W3010360545","https://openalex.org/W3025581723","https://openalex.org/W3128825919","https://openalex.org/W3154934206","https://openalex.org/W3163839574","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W3206531472","https://openalex.org/W4221156109","https://openalex.org/W4223652858","https://openalex.org/W4224916413","https://openalex.org/W4226046733","https://openalex.org/W4289792473","https://openalex.org/W4300833946","https://openalex.org/W4312096533","https://openalex.org/W6745136726","https://openalex.org/W6750665317","https://openalex.org/W6760184523","https://openalex.org/W6790312409","https://openalex.org/W6809939061"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4385352507","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W2388033618","https://openalex.org/W105599799","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Most":[0],"of":[1,15,132,159,166],"the":[2,26,69,76,80,85,97,122,130,133,157,164],"existing":[3,70],"neural-based":[4],"models":[5,37],"for":[6,29,59],"keyword":[7,143],"spotting":[8],"(KWS)":[9],"in":[10,156],"smart":[11,30],"devices":[12,31],"require":[13],"thousands":[14],"training":[16,134],"samples":[17,83],"to":[18,32,39,42,68,74,91,95,136,144],"learn":[19],"a":[20,52,146,153],"decent":[21],"audio":[22],"representation.":[23],"However,":[24],"with":[25],"rising":[27],"demand":[28],"become":[33],"more":[34],"person-alized,":[35],"KWS":[36],"need":[38],"adapt":[40],"quickly":[41],"smaller":[43],"user":[44],"samples.":[45,87],"To":[46],"tackle":[47],"this":[48],"challenge,":[49],"we":[50,128],"propose":[51],"contrastive":[53,66],"speech":[54,104],"mixup":[55,71],"(CosMix)":[56],"learning":[57],"algorithm":[58],"low-resource":[60,147],"KWS.":[61],"CosMix":[62],"introduces":[63],"an":[64],"auxiliary":[65],"loss":[67],"augmentation":[72],"technique":[73],"maximize":[75],"relative":[77],"similarity":[78],"between":[79],"original":[81],"pre-mixed":[82,115],"and":[84,113],"augmented":[86,108],"The":[88],"goal":[89],"is":[90],"inject":[92],"enhancing":[93],"constraints":[94],"guide":[96],"model":[98],"towards":[99],"simpler":[100],"but":[101],"richer":[102],"content-based":[103],"representations":[105],"from":[106],"two":[107],"views":[109],"(i.e.":[110],"noisy":[111],"mixed":[112],"clean":[114],"utterances).":[116],"We":[117],"conduct":[118],"our":[119,167],"experiments":[120],"on":[121],"Google":[123],"Speech":[124],"Command":[125],"dataset,":[126],"where":[127],"trim":[129],"size":[131],"set":[135],"as":[137,139],"small":[138],"2.5":[140],"mins":[141],"per":[142],"simulate":[145],"condition.":[148],"Our":[149],"experimental":[150],"results":[151],"show":[152],"consistent":[154],"improvement":[155],"performance":[158],"multiple":[160],"models,":[161],"which":[162],"exhibits":[163],"effectiveness":[165],"method.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}