{"id":"https://openalex.org/W3160056314","doi":"https://doi.org/10.1109/icassp39728.2021.9414501","title":"Dynamic Curriculum Learning via Data Parameters for Noise Robust Keyword Spotting","display_name":"Dynamic Curriculum Learning via Data Parameters for Noise Robust Keyword Spotting","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160056314","doi":"https://doi.org/10.1109/icassp39728.2021.9414501","mag":"3160056314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025685148","display_name":"Shreyas Saxena","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shreyas Saxena","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041575981","display_name":"Mehrez Souden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mehrez Souden","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102398357","display_name":"Tien Dung Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tien Dung Tran","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012541772","display_name":"Masood Delfarah","orcid":"https://orcid.org/0000-0002-8354-0832"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Masood Delfarah","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110720542","display_name":"Chandra Dhir","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chandra Dhir","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101768343"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.9518,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79686776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6848","last_page":"6852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9173659086227417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025567531585693},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7336980104446411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5988756418228149},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.553389310836792},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5074967741966248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4665294289588928},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4640445113182068},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4395084083080292},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41748926043510437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38945674896240234},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18052345514297485},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14873036742210388}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9173659086227417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025567531585693},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7336980104446411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5988756418228149},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.553389310836792},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5074967741966248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4665294289588928},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4640445113182068},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4395084083080292},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41748926043510437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38945674896240234},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18052345514297485},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14873036742210388},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1509793305","https://openalex.org/W1522301498","https://openalex.org/W1979651826","https://openalex.org/W1989314204","https://openalex.org/W1995562189","https://openalex.org/W2034940213","https://openalex.org/W2062164080","https://openalex.org/W2101045344","https://openalex.org/W2112739286","https://openalex.org/W2160815625","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398187210","https://openalex.org/W2400339399","https://openalex.org/W2407023693","https://openalex.org/W2515753980","https://openalex.org/W2517616541","https://openalex.org/W2591789009","https://openalex.org/W2775572503","https://openalex.org/W2884797218","https://openalex.org/W2889511491","https://openalex.org/W2900212944","https://openalex.org/W2962707338","https://openalex.org/W2962824709","https://openalex.org/W2964121744","https://openalex.org/W2982471419","https://openalex.org/W2991349609","https://openalex.org/W6631190155","https://openalex.org/W6714171909","https://openalex.org/W6747003534","https://openalex.org/W6770362605"],"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":{"We":[0,139],"propose":[1,72],"dynamic":[2],"curriculum":[3,59,75,123,126],"learning":[4,15,60,76,127],"via":[5],"data":[6,27,43,93,164],"parameters":[7,44,165],"for":[8,20,29,64,78],"noise":[9,113],"robust":[10],"keyword":[11,149],"spotting.":[12],"Data":[13],"parameter":[14],"has":[16],"recently":[17],"been":[18],"introduced":[19,35],"image":[21],"processing,":[22],"where":[23],"weight":[24],"parameters,":[25,28],"so-called":[26],"target":[30],"classes":[31,51,104],"and":[32,36,47,52,81,88,105,121],"instances":[33,53],"are":[34],"optimized":[37],"along":[38],"with":[39,91,162],"model":[40,85,170],"parameters.":[41,94],"The":[42,95],"scale":[45],"logits":[46],"control":[48],"importance":[49],"over":[50],"during":[54],"training,":[55],"which":[56,171],"enables":[57],"automatic":[58],"without":[61],"additional":[62],"annotations":[63],"training":[65],"data.":[66],"Similarly,":[67],"in":[68,116,158],"this":[69,74],"paper,":[70],"we":[71],"using":[73],"approach":[77,97,146],"acoustic":[79,84,137],"modeling,":[80],"train":[82],"an":[83],"on":[86,147,175],"clean":[87],"noisy":[89],"utterances":[90],"the":[92,100,103,117,133,136,141,144,163,176],"proposed":[96,145],"automatically":[98],"learns":[99],"difficulty":[101],"of":[102,132,135,143],"instances,":[106],"e.g.":[107],"due":[108],"to":[109,112,129,167],"low":[110],"speech":[111],"ratio":[114,161],"(SNR),":[115],"gradient":[118],"descent":[119],"optimization":[120],"performs":[122],"learning.":[124],"This":[125],"leads":[128],"overall":[130],"improvement":[131],"accuracy":[134],"model.":[138],"evaluate":[140],"effectiveness":[142],"a":[148,168],"spotting":[150],"task.":[151],"Experimental":[152],"results":[153],"show":[154],"7.7%":[155],"relative":[156],"reduction":[157],"false":[159],"reject":[160],"compared":[166],"base-line":[169],"is":[172],"simply":[173],"trained":[174],"multiconditioned":[177],"dataset.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}