{"id":"https://openalex.org/W7225157345","doi":"https://doi.org/10.48550/arxiv.2611.03271","title":"A Human-Verified AI Workflow for Annotating Environmental Sound Data","display_name":"A Human-Verified AI Workflow for Annotating Environmental Sound Data","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225157345","doi":"https://doi.org/10.48550/arxiv.2611.03271"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03271","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03271","pdf_url":"https://arxiv.org/pdf/2611.03271","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160519588","display_name":"Michael Barasa Murunga","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murunga, Michael Barasa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5098909703","display_name":"Allan Vikiru","orcid":"https://orcid.org/0000-0002-7739-5667","observed_orcids":["https://orcid.org/0000-0002-7739-5667"]},"institutions":[{"id":"https://openalex.org/I161372803","display_name":"Strathmore University","ror":"https://ror.org/047dnqw48","country_code":"KE","type":"education","lineage":["https://openalex.org/I161372803"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Vikiru, Allan","raw_affiliation_strings":["Conservation Technology Research Lab , Strathmore University , Ole Sangale Road , Nairobi , Kenya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conservation Technology Research Lab , Strathmore University , Ole Sangale Road , Nairobi , Kenya","institution_ids":["https://openalex.org/I161372803"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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":0.0008999999845400453,"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/T11692","display_name":"Noise Effects and Management","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3102","display_name":"Acoustics and Ultrasonics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-spectrogram-transformer","display_name":"Audio Spectrogram Transformer","score":0.8560000061988831},{"id":"https://openalex.org/keywords/zero-shot-classification","display_name":"zero-shot classification","score":0.7549999952316284},{"id":"https://openalex.org/keywords/annotation-efficiency","display_name":"annotation efficiency","score":0.48500001430511475},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.5019999742507935},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.30300000309944153}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8015000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743399977684021},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03271","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03271","pdf_url":"https://arxiv.org/pdf/2611.03271","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"},{"id":"doi:10.48550/arxiv.2611.03271","doi":"https://doi.org/10.48550/arxiv.2611.03271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03271","pdf_url":null,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03271","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03271","pdf_url":"https://arxiv.org/pdf/2611.03271","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225157345.pdf","grobid_xml":"https://content.openalex.org/works/W7225157345.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2809183397","https://openalex.org/W2941505948","https://openalex.org/W2539879360","https://openalex.org/W2809169812","https://openalex.org/W7131400360","https://openalex.org/W7162499925","https://openalex.org/W7170142201","https://openalex.org/W7129516040","https://openalex.org/W2052666245","https://openalex.org/W3208458525"],"abstract_inverted_index":{"Large-scale":[0],"annotation":[1,42],"of":[2,23,36,43,55,96,173],"environmental":[3],"sound":[4,16],"recordings":[5,58],"presents":[6],"significant":[7],"challenges":[8],"under":[9],"time":[10,162],"and":[11,20,34,69,86,117,135,149,216],"resource":[12],"constraints,":[13],"particularly":[14],"when":[15],"categories":[17],"are":[18],"imbalanced":[19],"only":[21],"part":[22],"a":[24,37,51,66,70,132],"dataset":[25],"has":[26],"been":[27],"labeled.":[28],"This":[29],"paper":[30],"describes":[31],"the":[32,44,104,123,181,187,204],"development":[33],"evaluation":[35],"human-AI":[38],"workflow":[39,183],"used":[40,114],"during":[41],"Kenya":[45],"Forest":[46],"Sounds":[47],"Dataset":[48],"(KFSD),":[49],"using":[50],"project-stage":[52],"working":[53],"collection":[54],"7,531":[56],"audio":[57],"across":[59],"21":[60],"categories.":[61],"We":[62],"investigated":[63],"zero-shot":[64],"classification,":[65],"feature-based":[67],"ensemble,":[68],"fine-tuned":[71,77],"Audio":[72],"Spectrogram":[73],"Transformer":[74],"(AST).":[75],"The":[76,142,158,201],"AST":[78],"achieved":[79],"89.36%":[80],"accuracy,":[81],"85.98%":[82],"precision,":[83],"89.24%":[84],"recall,":[85],"87.58%":[87],"F1":[88],"on":[89,186],"held-out":[90],"test":[91],"data":[92],"for":[93,108,138,178,218],"binary":[94],"classification":[95],"Person":[97],"talking.":[98],"Because":[99],"this":[100],"result":[101],"remained":[102,137],"below":[103],"predefined":[105],"95%":[106],"threshold":[107],"autonomous":[109],"annotation,":[110,180],"model":[111],"predictions":[112],"were":[113,129],"as":[115],"suggestions":[116],"subjected":[118],"to":[119,131,193],"human":[120],"verification.":[121],"Of":[122],"5,026":[124],"initially":[125],"unlabeled":[126],"recordings,":[127],"2,337":[128,146],"routed":[130],"speech-verification":[133],"queue":[134,189],"2,689":[136],"ordinary":[139],"manual":[140,179],"annotation.":[141],"verifier":[143],"reviewed":[144],"all":[145],"machine-labeled":[147],"files":[148],"detected":[150],"zero":[151],"false":[152],"positives,":[153],"yielding":[154],"100%":[155],"verification":[156,161,210],"accuracy.":[157],"observed":[159,212],"average":[160,171],"was":[163],"approximately":[164,191],"4.2":[165],"seconds":[166,175],"per":[167,176],"file.":[168],"At":[169],"an":[170],"rate":[172],"35":[174],"file":[177,208],"hybrid":[182],"reduced":[184],"work":[185],"remaining":[188],"from":[190],"48.9":[192],"28.9":[194],"person-hours,":[195],"saving":[196],"about":[197],"20.0":[198],"hours":[199],"(41%).":[200],"study":[202],"documents":[203],"model-selection":[205],"process,":[206],"provenance-aware":[207],"organization,":[209],"procedure,":[211],"errors,":[213],"practical":[214],"limitations,":[215],"opportunities":[217],"extending":[219],"AI":[220],"assistance":[221],"beyond":[222],"one":[223],"category.":[224]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}
