{"id":"https://openalex.org/W4403661808","doi":"https://doi.org/10.48550/arxiv.2409.08489","title":"Resource-Efficient Reference-Free Evaluation of Audio Captions","display_name":"Resource-Efficient Reference-Free Evaluation of Audio Captions","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4403661808","doi":"https://doi.org/10.48550/arxiv.2409.08489"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.08489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08489","pdf_url":"https://arxiv.org/pdf/2409.08489","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2409.08489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037744622","display_name":"Rehana Mahfuz","orcid":"https://orcid.org/0000-0002-9974-1137","observed_orcids":["https://orcid.org/0000-0002-9974-1137"]},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahfuz, Rehana","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053583465","display_name":"Yinyi Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Yinyi","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009801065","display_name":"Erik Visser","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visser, Erik","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I4210087596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.32690000534057617,"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":0.32690000534057617,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21739999949932098,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.13660000264644623,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-captioning","display_name":"audio captioning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/reference-free-evaluation","display_name":"reference-free evaluation","score":0.902999997138977},{"id":"https://openalex.org/keywords/confidence-measures","display_name":"confidence measures","score":0.7730000019073486},{"id":"https://openalex.org/keywords/self-confidence","display_name":"self-confidence","score":0.36800000071525574},{"id":"https://openalex.org/keywords/model-calibration","display_name":"model calibration","score":0.6330000162124634},{"id":"https://openalex.org/keywords/temperature-scaling","display_name":"temperature scaling","score":0.9179999828338623},{"id":"https://openalex.org/keywords/resource-limited-settings","display_name":"resource-limited settings","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9034355878829956},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6707590818405151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6077781915664673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41313421726226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2780792713165283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17370638251304626},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14796927571296692},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.08489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08489","pdf_url":"https://arxiv.org/pdf/2409.08489","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.08489","doi":"https://doi.org/10.48550/arxiv.2409.08489","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.08489","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.08489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08489","pdf_url":"https://arxiv.org/pdf/2409.08489","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-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403661808.pdf","grobid_xml":"https://content.openalex.org/works/W4403661808.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403"],"abstract_inverted_index":{"To":[0,32,48],"establish":[1],"the":[2,41],"trustworthiness":[3],"of":[4,72,90,101,109],"systems":[5],"that":[6,57],"automatically":[7],"generate":[8],"text":[9],"captions":[10,110],"for":[11,106],"audio,":[12],"images":[13],"and":[14],"video,":[15],"existing":[16],"reference-free":[17,107],"metrics":[18,38,53,75,92,105],"rely":[19],"on":[20],"large":[21],"pretrained":[22],"models":[23],"which":[24],"are":[25],"impractical":[26],"to":[27,39],"accommodate":[28],"in":[29,44,111],"resource-constrained":[30,112],"settings.":[31,113],"address":[33],"this,":[34],"we":[35,61,83],"propose":[36],"some":[37,71],"elicit":[40],"model's":[42],"confidence":[43,74,91,104],"its":[45],"own":[46],"generation.":[47],"assess":[49],"how":[50],"well":[51],"these":[52,73],"replace":[54],"correctness":[55,66,80],"measures":[56],"leverage":[58],"reference":[59],"captions,":[60],"test":[62],"their":[63],"calibration":[64],"with":[65,78],"measures.":[67,81],"We":[68],"discuss":[69],"why":[70,87],"align":[76],"better":[77],"certain":[79],"Further,":[82],"provide":[84],"insight":[85],"into":[86],"temperature":[88],"scaling":[89],"is":[93,98],"effective.":[94],"Our":[95],"main":[96],"contribution":[97],"a":[99],"suite":[100],"well-calibrated":[102],"lightweight":[103],"evaluation":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-10-23T00:00:00"}