{"id":"https://openalex.org/W7214809226","doi":"https://doi.org/10.48550/arxiv.2609.30469","title":"Pretrained ASR Pseudo-labeling for Noisy Police Audio","display_name":"Pretrained ASR Pseudo-labeling for Noisy Police Audio","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214809226","doi":"https://doi.org/10.48550/arxiv.2609.30469"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.30469","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30469","pdf_url":"https://arxiv.org/pdf/2609.30469","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.30469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095094640","display_name":"Kaavya Chaparala","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaparala, Kaavya","raw_affiliation_strings":["Johns Hopkins University , Baltimore , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , Baltimore , USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153535436","display_name":"Su Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Su","raw_affiliation_strings":["Johns Hopkins University , Baltimore , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , Baltimore , USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153425845","display_name":"Stephen L. Miller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morgan, Stephen L.","raw_affiliation_strings":["Johns Hopkins University , Baltimore , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , Baltimore , USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016987307","display_name":"Rhiannon N. Miller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196272386","display_name":"Providence College","ror":"https://ror.org/00rxpqe74","country_code":"US","type":"education","lineage":["https://openalex.org/I196272386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miller, Rhiannon N.","raw_affiliation_strings":["Providence College , Providence , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Providence College , Providence , USA","institution_ids":["https://openalex.org/I196272386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153408903","display_name":"Anjalie Field","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Field, Anjalie","raw_affiliation_strings":["Johns Hopkins University , Baltimore , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University , Baltimore , USA","institution_ids":["https://openalex.org/I145311948"]}]}],"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":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/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/T11309","display_name":"Music and Audio Processing","score":0.0,"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/pseudo-labeling","display_name":"pseudo-labeling","score":0.8740000128746033},{"id":"https://openalex.org/keywords/noisy-speech-recognition","display_name":"noisy speech recognition","score":0.7649999856948853},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.7950000166893005},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.781000018119812},{"id":"https://openalex.org/keywords/confidence-measures","display_name":"confidence measures","score":0.7269999980926514},{"id":"https://openalex.org/keywords/police-decision-making","display_name":"police decision-making","score":0.5899999737739563},{"id":"https://openalex.org/keywords/chicago","display_name":"Chicago","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434000015258789},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6362000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5561000108718872},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.30469","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30469","pdf_url":"https://arxiv.org/pdf/2609.30469","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.30469","doi":"https://doi.org/10.48550/arxiv.2609.30469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.30469","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.30469","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30469","pdf_url":"https://arxiv.org/pdf/2609.30469","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214809226.pdf","grobid_xml":"https://content.openalex.org/works/W7214809226.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2889048668","https://openalex.org/W3026041220","https://openalex.org/W3096338464","https://openalex.org/W4311000453","https://openalex.org/W4387994971","https://openalex.org/W4390041933","https://openalex.org/W7126278909"],"related_works":["https://openalex.org/W4307927978","https://openalex.org/W4225529283","https://openalex.org/W4416401420","https://openalex.org/W4415068063","https://openalex.org/W3201101490","https://openalex.org/W4415432690","https://openalex.org/W7124459703","https://openalex.org/W4394780796","https://openalex.org/W4319862240","https://openalex.org/W4385570493"],"abstract_inverted_index":{"Pretrained":[0],"ASR":[1,24,57],"systems":[2],"perform":[3],"poorly":[4],"on":[5,35],"noisy":[6,37,63],"Broadcast":[7],"Police":[8],"Communication":[9],"(BPC),":[10],"hindering":[11],"efforts":[12],"to":[13,22,54,62,83,104,139],"understand":[14],"police":[15],"decision-making.":[16],"Pseudo-labeling":[17],"offers":[18],"an":[19,95,140],"unsupervised":[20],"path":[21],"improve":[23],"without":[25],"expensive":[26],"human":[27],"labels,":[28],"but":[29],"the":[30,48,122,127,159],"efficacy":[31],"of":[32,52,121],"this":[33,43,164],"approach":[34],"very":[36],"domains":[38],"is":[39,154],"not":[40],"known.":[41],"In":[42],"work,":[44],"we":[45,93,162],"systematically":[46],"assess":[47],"opportunities":[49],"and":[50,60,69,79,87,92,117,129,161],"limits":[51],"pseudo-labeling":[53,149,172],"adapt":[55],"foundation":[56],"models":[58],"(Whisper":[59],"Qwen3-ASR)":[61],"BPC":[64,90,131],"domain":[65],"corpora":[66],"from":[67,158],"Baltimore":[68,128],"Chicago.":[70],"We":[71,143],"demonstrate":[72],"that":[73,100],"existing":[74],"internal":[75,115],"confidence":[76],"metrics":[77,116],"(log-probabilities":[78],"STAR":[80],"scores)":[81],"fail":[82],"distinguish":[84],"between":[85],"high":[86],"low":[88],"quality":[89],"pseudo-labels,":[91],"introduce":[94,145],"external":[96],"LLM-as-a-judge":[97],"filtering":[98],"paradigm":[99,150],"leverages":[101],"parametric":[102],"knowledge":[103],"discard":[105],"contextually":[106],"implausible":[107],"transcripts.":[108],"Our":[109],"LLM-judging":[110],"filters":[111],"more":[112],"aggressively":[113],"than":[114],"significantly":[118],"reduces":[119],"WER":[120],"pseudo-labeled":[123],"training":[124],"sets":[125],"across":[126],"Chicago":[130],"corpora,":[132],"though":[133],"a":[134,146,167],"substantial":[135],"gap":[136],"remains":[137],"relative":[138],"oracle":[141],"filter.":[142],"also":[144],"new":[147],"cross-model":[148],"where":[151],"one":[152],"model":[153],"finetuned":[155],"with":[156],"pseudo-labels":[157],"other,":[160],"identify":[163],"method":[165],"as":[166],"promising":[168],"direction":[169],"for":[170],"future":[171],"work.":[173]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}