{"id":"https://openalex.org/W4226046733","doi":"https://doi.org/10.1109/icassp43922.2022.9747025","title":"Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting","display_name":"Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226046733","doi":"https://doi.org/10.1109/icassp43922.2022.9747025"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747025","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group,Beijing","School of Computer Science and Engineering, Nanyang Technological University, Singapore","Alibaba Group, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Beijing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Alibaba Group, Beijing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101943352","display_name":"Yunqi Chen","orcid":"https://orcid.org/0000-0003-4343-862X"},"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/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yunqi Chen","raw_affiliation_strings":["Alibaba Group,Beijing","Alibaba Group, Beijing","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Beijing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Beijing","institution_ids":["https://openalex.org/I45928872"]},{"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/A5069657933","display_name":"Biao Tian","orcid":"https://orcid.org/0000-0001-7259-3739"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Tian","raw_affiliation_strings":["Alibaba Group,Beijing","Alibaba Group, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Beijing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Beijing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065153972","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0003-4100-2777"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Alibaba Group,Beijing","Alibaba Group, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Beijing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Beijing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","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"],"raw_orcid":null,"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3603","last_page":"3607"},"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":0.9998000264167786,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8273028135299683},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7388941645622253},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7383477091789246},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6365823745727539},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5571145415306091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405624508857727},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5124703049659729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5081942081451416},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.468201220035553},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41335320472717285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3767617344856262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32445400953292847},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09788045287132263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273028135299683},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7388941645622253},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7383477091789246},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6365823745727539},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5571145415306091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405624508857727},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5124703049659729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5081942081451416},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.468201220035553},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41335320472717285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767617344856262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32445400953292847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09788045287132263},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747025","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W2034940213","https://openalex.org/W2219249508","https://openalex.org/W2407023693","https://openalex.org/W2531409750","https://openalex.org/W2584329820","https://openalex.org/W2766245080","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2901243971","https://openalex.org/W2953219395","https://openalex.org/W2963390466","https://openalex.org/W2964187693","https://openalex.org/W3025581723","https://openalex.org/W3096976027","https://openalex.org/W3097018422","https://openalex.org/W3157506437","https://openalex.org/W3162090017","https://openalex.org/W3196496149","https://openalex.org/W3196974791","https://openalex.org/W3198035615","https://openalex.org/W4320930577","https://openalex.org/W6746023985","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6795140394"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Building":[0],"efficient":[1,84],"architecture":[2],"in":[3,11,70],"neural":[4,29],"speech":[5],"processing":[6],"is":[7,17,38,68,90,109],"paramount":[8],"to":[9,23,57,92],"success":[10],"keyword":[12],"spotting":[13],"deployment.":[14],"However,":[15],"it":[16],"very":[18],"challenging":[19],"for":[20],"lightweight":[21],"models":[22,114],"achieve":[24],"noise":[25,95,118],"robustness":[26],"with":[27,53,82],"concise":[28],"operations.":[30],"In":[31],"a":[32,47],"real-world":[33],"application,":[34],"the":[35,61,73,78,116],"user":[36],"environment":[37],"typically":[39],"noisy":[40,62],"and":[41,108],"may":[42],"contain":[43],"reverberations.":[44],"We":[45],"proposed":[46,69],"novel":[48],"feature":[49],"interactive":[50,66],"convolutional":[51],"model":[52,98],"merely":[54],"100K":[55],"parameters":[56],"tackle":[58],"this":[59],"under":[60,115],"far-field":[63],"condition.":[64,119],"The":[65],"unit":[67],"place":[71],"of":[72,80],"attention":[74],"module":[75],"that":[76],"promotes":[77],"flow":[79],"information":[81],"more":[83],"computations.":[85],"Moreover,":[86],"curriculum-based":[87],"multi-condition":[88],"training":[89],"adopted":[91],"attain":[93],"better":[94],"robustness.":[96],"Our":[97],"achieves":[99],"98.2%":[100],"top-1":[101],"accuracy":[102],"on":[103],"Google":[104],"Speech":[105],"Command":[106],"V2-12":[107],"competitive":[110],"against":[111],"large":[112],"transformer":[113],"designed":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2022-05-05T00:00:00"}