{"id":"https://openalex.org/W4375869156","doi":"https://doi.org/10.1109/icassp49357.2023.10096526","title":"A Novel Metric For Evaluating Audio Caption Similarity","display_name":"A Novel Metric For Evaluating Audio Caption Similarity","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869156","doi":"https://doi.org/10.1109/icassp49357.2023.10096526"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5009006680","display_name":"Swapnil Bhosale","orcid":"https://orcid.org/0000-0001-8299-7569"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swapnil Bhosale","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,India","TCS Research, Tata Consultancy Services Limited, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"TCS Research, Tata Consultancy Services Limited, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077689139","display_name":"Rupayan Chakraborty","orcid":"https://orcid.org/0000-0002-3566-0784"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupayan Chakraborty","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,India","TCS Research, Tata Consultancy Services Limited, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"TCS Research, Tata Consultancy Services Limited, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,India","TCS Research, Tata Consultancy Services Limited, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"TCS Research, Tata Consultancy Services Limited, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8982,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75791216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T11309","display_name":"Music 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/T11439","display_name":"Video Analysis and Summarization","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8165955543518066},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7993300557136536},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7665154933929443},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6592843532562256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6370014548301697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5665504932403564},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5367869734764099},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.516105055809021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4466634690761566},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41905859112739563},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19324132800102234},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09567859768867493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165955543518066},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7993300557136536},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7665154933929443},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6592843532562256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6370014548301697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5665504932403564},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5367869734764099},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.516105055809021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4466634690761566},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41905859112739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19324132800102234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09567859768867493},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1622490909","https://openalex.org/W1956340063","https://openalex.org/W2050968192","https://openalex.org/W2116206474","https://openalex.org/W2506483933","https://openalex.org/W2770119437","https://openalex.org/W2775794021","https://openalex.org/W2793286954","https://openalex.org/W2907743838","https://openalex.org/W2936695845","https://openalex.org/W2940092410","https://openalex.org/W2964213897","https://openalex.org/W2982554818","https://openalex.org/W3015591594","https://openalex.org/W3038899388","https://openalex.org/W3163843406","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6746278845","https://openalex.org/W6761205521","https://openalex.org/W6780379688","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W4388002133","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Automatic":[0],"Audio":[1],"Captioning":[2],"(AAC)":[3],"refers":[4],"to":[5,41,46,51,67,76,80],"the":[6,34],"task":[7],"of":[8],"describing":[9],"an":[10],"audio":[11],"sample":[12],"in":[13,49,84],"a":[14,59],"natural":[15],"language":[16],"(NL)":[17],"text.":[18],"Unlike":[19],"NL":[20,43,85],"text":[21,44,86],"generation":[22],"tasks,":[23],"which":[24],"rely":[25],"on":[26,63],"lexical":[27,52],"semantic":[28],"metrics":[29,82],"like":[30],"BLEU":[31],"for":[32,91],"evaluation,":[33],"AAC":[35],"evaluation":[36,74],"metric":[37,61,75],"requires":[38],"acoustic":[39,69],"semantics":[40],"map":[42],"corresponding":[45],"similar":[47],"sounds":[48],"addition":[50],"semantics.":[53,70],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"novel":[60],"based":[62],"Text-to-Audio":[64],"Grounding":[65],"(TAG),":[66],"incorporate":[68],"Experiments":[71],"demonstrate":[72],"our":[73],"perform":[77],"better":[78],"compared":[79],"existing":[81],"used":[83],"and":[87],"image":[88],"captioning":[89],"literature":[90],"AAC.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
