{"id":"https://openalex.org/W4408355212","doi":"https://doi.org/10.1109/icassp49660.2025.10890176","title":"Toward noise-robust whisper keyword spotting on headphones with in-earcup microphone and curriculum learning","display_name":"Toward noise-robust whisper keyword spotting on headphones with in-earcup microphone and curriculum learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355212","doi":"https://doi.org/10.1109/icassp49660.2025.10890176"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5039386793","display_name":"Qiaoyu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaoyu Yang","raw_affiliation_strings":["University of Rochester,Rochester,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450332","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0001-5197-6028"},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bose Corporation,Framingham,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,Framingham,USA","institution_ids":["https://openalex.org/I76587968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085831884","display_name":"Chuan-Che Jeff Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76587968","display_name":"Bose (United States)","ror":"https://ror.org/0427k1a73","country_code":"US","type":"company","lineage":["https://openalex.org/I76587968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuan-Che Jeff Huang","raw_affiliation_strings":["Bose Corporation,Framingham,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bose Corporation,Framingham,USA","institution_ids":["https://openalex.org/I76587968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9776999950408936,"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":0.9531000256538391,"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/headphones","display_name":"Headphones","score":0.9157657027244568},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8266676664352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72530597448349},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6564236283302307},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5578234195709229},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5383646488189697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45118504762649536},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3296138048171997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28819549083709717},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2741418182849884},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1277391016483307}],"concepts":[{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.9157657027244568},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8266676664352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72530597448349},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6564236283302307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5578234195709229},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5383646488189697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45118504762649536},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3296138048171997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28819549083709717},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2741418182849884},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1277391016483307},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W4408353962","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539"],"abstract_inverted_index":{"The":[0],"expanding":[1],"feature":[2,24,46],"set":[3,47],"of":[4,13,36,65,96,122,137,149,159],"modern":[5],"headphones":[6,117],"puts":[7],"a":[8,56,73,128],"challenge":[9],"on":[10,115],"the":[11,45,60,94,112,135,147],"design":[12,127],"their":[14],"control":[15,22],"interface.":[16],"Users":[17],"may":[18,39,79],"want":[19],"to":[20,59,106,165],"separately":[21],"each":[23],"or":[25,86],"quickly":[26],"switch":[27],"between":[28],"modes":[29],"that":[30,132,146],"activate":[31],"different":[32],"features.":[33],"Traditional":[34],"approach":[35],"physical":[37],"buttons":[38],"no":[40],"longer":[41],"be":[42,81],"feasible":[43],"when":[44],"is":[48,55],"large.":[49],"Keyword":[50],"spotting":[51,67,99,162],"with":[52],"voice":[53,78,102,123],"commands":[54,70],"promising":[57],"solution":[58],"issue.":[61],"Most":[62],"existing":[63],"methods":[64],"keyword":[66,98,161],"only":[68],"support":[69],"spoken":[71],"in":[72,83,100,167],"regular":[74,77],"voice.":[75],"However,":[76],"not":[80],"desirable":[82],"quiet":[84],"places":[85],"public":[87],"settings.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"investigate":[93],"problem":[95],"on-device":[97],"whisper":[101,138,160],"and":[103,152],"explore":[104],"approaches":[105],"improve":[107,156],"noise":[108],"robustness.":[109],"We":[110,125,142],"leverage":[111],"inner":[113],"microphone":[114],"noise-cancellation":[116],"as":[118],"an":[119],"additional":[120],"source":[121],"input.":[124],"also":[126],"curriculum":[129,153],"learning":[130,154],"strategy":[131],"gradually":[133],"increases":[134],"proportion":[136],"keywords":[139],"during":[140],"training.":[141],"demonstrate":[143],"through":[144],"experiments":[145],"combination":[148],"multi-microphone":[150],"processing":[151],"could":[155],"F1":[157],"score":[158],"by":[163],"up":[164],"15%":[166],"noisy":[168],"conditions.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}