{"id":"https://openalex.org/W4414713362","doi":"https://doi.org/10.21437/wocci.2025-8","title":"Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications","display_name":"Adapting Whisper for Lightweight and Efficient Automatic Speech Recognition of Children for On-device Edge Applications","publication_year":2025,"publication_date":"2025-08-22","ids":{"openalex":"https://openalex.org/W4414713362","doi":"https://doi.org/10.21437/wocci.2025-8"},"language":"en","primary_location":{"id":"doi:10.21437/wocci.2025-8","doi":"https://doi.org/10.21437/wocci.2025-8","is_oa":false,"landing_page_url":"https://doi.org/10.21437/wocci.2025-8","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop on Child Computer Interaction - WOCCI 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081044590","display_name":"Satwik Dutta","orcid":"https://orcid.org/0000-0001-5880-7454","observed_orcids":["https://orcid.org/0000-0001-5880-7454"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satwik Dutta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119799494","display_name":"Shruthigna Chandupatla","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shruthigna Chandupatla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9483,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74898837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/whisper","display_name":"Whisper","score":0.9440000057220459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8209999799728394},{"id":"https://openalex.org/keywords/children-s-speech","display_name":"children's speech","score":0.746999979019165},{"id":"https://openalex.org/keywords/on-device-inference","display_name":"on-device inference","score":0.8650000095367432},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.9129999876022339},{"id":"https://openalex.org/keywords/raspberry-pi","display_name":"Raspberry Pi","score":0.925000011920929},{"id":"https://openalex.org/keywords/low-rank-compression","display_name":"low-rank compression","score":0.8059999942779541},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.5640000104904175},{"id":"https://openalex.org/keywords/thermal-throttling","display_name":"thermal throttling","score":0.7350000143051147},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5583999752998352},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.34450000524520874},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.34369999170303345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/wocci.2025-8","doi":"https://doi.org/10.21437/wocci.2025-8","is_oa":false,"landing_page_url":"https://doi.org/10.21437/wocci.2025-8","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop on Child Computer Interaction - WOCCI 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.14451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14451","pdf_url":"https://arxiv.org/pdf/2507.14451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14451","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14451","pdf_url":"https://arxiv.org/pdf/2507.14451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385822587","https://openalex.org/W7155518592","https://openalex.org/W4392908601","https://openalex.org/W7154901180","https://openalex.org/W4414943721","https://openalex.org/W4417053970","https://openalex.org/W4404518524","https://openalex.org/W4400025583","https://openalex.org/W7215391324","https://openalex.org/W4416037060"],"abstract_inverted_index":{"Reliability":[0],"on":[1,41,95],"cloud":[2],"providers":[3],"for":[4,107,114],"ASR":[5,36],"inference":[6,85,94],"to":[7,16,29,57],"support":[8],"child-centered":[9],"voice-based":[10],"applications":[11],"is":[12],"becoming":[13],"challenging":[14],"due":[15],"regulatory":[17],"and":[18,51,123],"privacy":[19],"challenges.":[20],"Motivated":[21],"by":[22,52,80],"a":[23,31,42,62],"privacy-preserving":[24],"design,":[25],"this":[26],"study":[27],"aims":[28],"develop":[30],"lightweight":[32],"&":[33],"efficient":[34],"Whisper":[35],"system":[37],"capable":[38,131],"of":[39,47,67,132],"running":[40],"Raspberry":[43],"Pi.":[44],"Upon":[45],"evaluation":[46],"the":[48,59,77,97,109,120,128,135],"MyST":[49],"corpus":[50],"examining":[53],"various":[54,115],"filtering":[55],"strategies":[56],"fine-tune":[58],"`tiny.en'":[60],"model,":[61],"Word":[63],"Error":[64],"Rate":[65],"(WER)":[66],"15.9%":[68],"was":[69,130,140],"achieved":[70],"(11.8%":[71],"filtered).":[72],"A":[73],"low-rank":[74],"compression":[75],"reduces":[76],"encoder":[78],"size":[79],"0.51M":[81],"with":[82,88],"1.26x":[83],"faster":[84],"in":[86],"GPU,":[87],"11%":[89],"relative":[90],"WER":[91],"increase.":[92],"During":[93],"Pi,":[96],"compressed":[98],"version":[99],"required":[100],"~2":[101],"GFLOPS":[102],"fewer":[103],"computations.":[104],"The":[105],"RTF":[106],"both":[108,134],"models":[110,144],"ranged":[111],"between":[112],"[0.23-0.41]":[113],"input":[116],"audio":[117],"durations.":[118],"Analyzing":[119],"RAM":[121],"usage":[122],"CPU":[124],"temperature":[125],"showed":[126],"that":[127,142],"PI":[129],"handling":[133],"tiny":[136],"models,":[137],"however":[138],"it":[139],"noticed":[141],"small":[143],"initiated":[145],"additional":[146],"overhead/thermal":[147],"throttling.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2025-10-10T00:00:00"}