{"id":"https://openalex.org/W4281646171","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892207","title":"Speech Augmentation Based Unsupervised Learning for Keyword Spotting","display_name":"Speech Augmentation Based Unsupervised Learning for Keyword Spotting","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4281646171","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892207"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892207","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","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/A5100608965","display_name":"Jianbin Luo","orcid":"https://orcid.org/0000-0002-5132-0712"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Jian Luo","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065576761","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0003-0909-5328"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055352265","display_name":"Haobin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Tang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd","University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100608965"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.38267615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987999796867371,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8425102233886719},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8140918016433716},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.7647576332092285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6704597473144531},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6075451374053955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5689758062362671},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4776647984981537},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.42753395438194275},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37908002734184265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37362784147262573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3647148013114929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425102233886719},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8140918016433716},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.7647576332092285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6704597473144531},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6075451374053955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5689758062362671},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4776647984981537},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.42753395438194275},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37908002734184265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37362784147262573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3647148013114929},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892207","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1544266773","https://openalex.org/W1734538896","https://openalex.org/W1922655562","https://openalex.org/W2034940213","https://openalex.org/W2099415988","https://openalex.org/W2099621636","https://openalex.org/W2126203737","https://openalex.org/W2153426278","https://openalex.org/W2407023693","https://openalex.org/W2407080277","https://openalex.org/W2587529061","https://openalex.org/W2622203030","https://openalex.org/W2697044473","https://openalex.org/W2785325870","https://openalex.org/W2797583228","https://openalex.org/W2809099079","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2938873567","https://openalex.org/W2953219395","https://openalex.org/W2963414149","https://openalex.org/W2964187693","https://openalex.org/W2972818416","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2981991061","https://openalex.org/W3007328579","https://openalex.org/W3015995734","https://openalex.org/W3019293601","https://openalex.org/W3026041220","https://openalex.org/W3035837245","https://openalex.org/W3095776571","https://openalex.org/W3097018422","https://openalex.org/W3098773154","https://openalex.org/W3119913666","https://openalex.org/W3138218066","https://openalex.org/W3144810982","https://openalex.org/W3145755240","https://openalex.org/W3150269179","https://openalex.org/W3160864104","https://openalex.org/W3196798358","https://openalex.org/W3197949759","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6632425017","https://openalex.org/W6640090968","https://openalex.org/W6675409298","https://openalex.org/W6739901393","https://openalex.org/W6747899497","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6769238691","https://openalex.org/W6779216093","https://openalex.org/W6781428138","https://openalex.org/W6792479393","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"In":[0,136],"this":[1],"paper,":[2],"we":[3,63],"investigated":[4],"a":[5,19,33],"speech":[6,21,83,93],"augmentation":[7,94,123,140],"based":[8,74,124,141],"unsupervised":[9,67,71,100,125,142,152],"learning":[10,68,126],"approach":[11],"for":[12],"keyword":[13],"spotting":[14],"(KWS)":[15],"task.":[16,40,135],"KWS":[17,39,61,134,145],"is":[18,73],"useful":[20],"application,":[22],"yet":[23],"also":[24,64],"heavily":[25],"depends":[26],"on":[27,44,75,107],"the":[28,38,45,53,58,76,79,88,99,122,130],"labeled":[29],"data.":[30],"We":[31],"designed":[32],"CNN-Attention":[34,116],"architecture":[35],"to":[36],"conduct":[37],"CNN":[41],"layers":[42,51],"focus":[43],"local":[46],"acoustic":[47],"features,":[48,84],"and":[49,81,103,158],"attention":[50],"model":[52,117,146],"long-time":[54],"dependency.":[55],"To":[56],"improve":[57,129],"robustness":[59],"of":[60,133],"model,":[62],"proposed":[65],"an":[66],"method.":[69],"The":[70,105],"loss":[72],"similarity":[77],"between":[78],"original":[80],"augmented":[82],"as":[85,87,155],"well":[86],"audio":[89],"reconstructing":[90],"information.":[91],"Two":[92],"methods":[95],"are":[96],"explored":[97],"in":[98],"learning:":[101],"speed":[102],"intensity.":[104],"experiments":[106],"Google":[108],"Speech":[109],"Commands":[110],"V2":[111],"Dataset":[112],"demonstrated":[113],"that":[114],"our":[115,137,144],"has":[118],"competitive":[119],"results.":[120],"Moreover,":[121],"could":[127],"further":[128],"classification":[131],"accuracy":[132],"experiments,":[138],"with":[139],"learning,":[143],"achieves":[147],"better":[148],"performance":[149],"than":[150],"other":[151],"methods,":[153],"such":[154],"CPC,":[156],"APC,":[157],"MPC.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}