{"id":"https://openalex.org/W4225272619","doi":"https://doi.org/10.1109/icassp43922.2022.9747227","title":"Nonverbal Sound Detection for Disordered Speech","display_name":"Nonverbal Sound Detection for Disordered Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225272619","doi":"https://doi.org/10.1109/icassp43922.2022.9747227"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747227","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":"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/A5088537496","display_name":"Colin Lea","orcid":"https://orcid.org/0000-0001-7068-3351"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Colin Lea","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110297973","display_name":"Zifang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zifang Huang","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002130285","display_name":"Dhruv Jain","orcid":"https://orcid.org/0000-0002-0343-8126"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruv Jain","raw_affiliation_strings":["Apple Inc","University of Washington"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070832337","display_name":"Lauren Tooley","orcid":"https://orcid.org/0000-0002-3890-5636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lauren Tooley","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085425943","display_name":"Zeinab Liaghat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeinab Liaghat","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067932263","display_name":"Shrinath Thelapurath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrinath Thelapurath","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031744461","display_name":"Leah Findlater","orcid":"https://orcid.org/0000-0002-5619-4452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leah Findlater","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082603621","display_name":"Jeffrey P. Bigham","orcid":"https://orcid.org/0000-0002-2072-0625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey P. Bigham","raw_affiliation_strings":["Apple Inc"],"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5088537496"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73071536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7397","last_page":"7401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606834173202515},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6867051720619202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6018881797790527},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5922785997390747},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.5216008424758911},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.47947320342063904},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.45022743940353394},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4359624981880188},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41376930475234985},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3330804705619812},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14151984453201294},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10858827829360962},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09535545110702515},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08622586727142334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606834173202515},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6867051720619202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6018881797790527},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5922785997390747},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.5216008424758911},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.47947320342063904},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.45022743940353394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4359624981880188},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41376930475234985},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3330804705619812},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14151984453201294},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10858827829360962},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09535545110702515},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08622586727142334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747227","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":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983020750","https://openalex.org/W2006277158","https://openalex.org/W2033333932","https://openalex.org/W2094958958","https://openalex.org/W2133739410","https://openalex.org/W2151936436","https://openalex.org/W2187089797","https://openalex.org/W2593116425","https://openalex.org/W2595767284","https://openalex.org/W2909828837","https://openalex.org/W2914315283","https://openalex.org/W3015537910","https://openalex.org/W3030488821","https://openalex.org/W3045297130","https://openalex.org/W3080894165","https://openalex.org/W3144247233","https://openalex.org/W3163725792","https://openalex.org/W3196404988","https://openalex.org/W3197712601","https://openalex.org/W6734260513","https://openalex.org/W6759131349","https://openalex.org/W6781991486","https://openalex.org/W6800224916"],"related_works":["https://openalex.org/W2083826984","https://openalex.org/W30434212","https://openalex.org/W2109868656","https://openalex.org/W2110156781","https://openalex.org/W2368779261","https://openalex.org/W2150689955","https://openalex.org/W1965658093","https://openalex.org/W1892128710","https://openalex.org/W2124343046","https://openalex.org/W4225272619"],"abstract_inverted_index":{"Voice":[0],"assistants":[1],"have":[2,50,60],"become":[3],"an":[4,70,142],"essential":[5],"tool":[6],"for":[7,22,36,121],"people":[8],"with":[9,28,42],"various":[10],"disabilities":[11],"because":[12],"they":[13],"enable":[14],"complex":[15],"phone-or":[16],"tablet-based":[17],"interactions":[18],"without":[19],"the":[20,37,114,170],"need":[21],"fine-grained":[23],"motor":[24],"control,":[25],"such":[26,157],"as":[27,158],"touchscreens.":[29],"However,":[30],"these":[31],"systems":[32],"are":[33,54,65],"not":[34],"tuned":[35],"unique":[38],"characteristics":[39],"of":[40,47,58,98,116,137,145,167],"individuals":[41],"speech":[43,100],"disorders,":[44],"including":[45],"many":[46],"those":[48],"who":[49],"a":[51,61,117],"motor-speech":[52],"disorder,":[53],"deaf":[55],"or":[56,64,89],"hard":[57],"hearing,":[59],"severe":[62],"stutter,":[63],"minimally":[66],"verbal.":[67],"We":[68],"introduce":[69],"alternative":[71],"voice-based":[72],"input":[73],"system":[74,92],"which":[75],"relies":[76],"on":[77,141,155],"sound":[78],"event":[79],"detection":[80],"using":[81],"fifteen":[82],"nonverbal":[83],"mouth":[84],"sounds":[85],"like":[86],"\"pop\",":[87],"\"click\",":[88],"\"eh.\"":[90],"This":[91],"was":[93],"designed":[94],"to":[95,106],"work":[96],"regardless":[97],"ones\u2019":[99],"abilities":[101],"and":[102,124,135,139],"allows":[103],"full":[104],"access":[105],"existing":[107],"technology.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112],"describe":[113],"design":[115],"dataset,":[118],"model":[119,127,131,172],"considerations":[120],"real-world":[122],"deployment,":[123],"efforts":[125],"towards":[126],"personalization.":[128],"Our":[129],"fully-supervised":[130],"achieves":[132],"segment-level":[133],"precision":[134],"recall":[136],"88.6%":[138],"88.4%":[140],"internal":[143],"dataset":[144],"710":[146],"adults,":[147],"while":[148],"achieving":[149],"0.31":[150],"false":[151],"positives":[152],"per":[153],"hour":[154],"aggressors":[156],"speech.":[159],"Five-shot":[160],"personalization":[161],"enables":[162],"satisfactory":[163],"performance":[164],"in":[165],"84.5%":[166],"cases":[168],"where":[169],"generic":[171],"fails.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
