{"id":"https://openalex.org/W4372341409","doi":"https://doi.org/10.1109/icassp49357.2023.10096522","title":"Improving Audio Captioning Using Semantic Similarity Metrics","display_name":"Improving Audio Captioning Using Semantic Similarity Metrics","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341409","doi":"https://doi.org/10.1109/icassp49357.2023.10096522"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096522","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096522","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/A5037744622","display_name":"Rehana Mahfuz","orcid":"https://orcid.org/0000-0002-9974-1137"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Rehana Mahfuz","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053583465","display_name":"Yinyi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yinyi Guo","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009801065","display_name":"Erik Visser","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erik Visser","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037744622"],"corresponding_institution_ids":["https://openalex.org/I19268510"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70159624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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/closed-captioning","display_name":"Closed captioning","score":0.8760033845901489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8572047352790833},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7096292972564697},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6688857078552246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5945632457733154},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5758934020996094},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5676941275596619},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5654135942459106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5532023906707764},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3504435420036316},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21685951948165894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07862278819084167}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8760033845901489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572047352790833},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7096292972564697},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6688857078552246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5945632457733154},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5758934020996094},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5676941275596619},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5654135942459106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532023906707764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3504435420036316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21685951948165894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07862278819084167},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096522","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096522","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1956340063","https://openalex.org/W2103235956","https://openalex.org/W2123301721","https://openalex.org/W2144211451","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2896457183","https://openalex.org/W2970641574","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W3205860970","https://openalex.org/W4296607943","https://openalex.org/W4385245566","https://openalex.org/W6621906925","https://openalex.org/W6678262379","https://openalex.org/W6681226105","https://openalex.org/W6682631176","https://openalex.org/W6725318829","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6844068664","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W4388002133","https://openalex.org/W3217195652"],"abstract_inverted_index":{"Audio":[0],"captioning":[1,14,92,114],"quality":[2],"metrics":[3,108],"which":[4],"are":[5],"typically":[6],"borrowed":[7],"from":[8],"the":[9,17,61,81,110],"machine":[10],"translation":[11],"and":[12,24,40,65,90,109],"image":[13],"areas":[15],"measure":[16],"degree":[18],"of":[19,44],"overlap":[20],"between":[21,38],"predicted":[22,39,101],"tokens":[23],"gold":[25],"reference":[26,41],"tokens.":[27],"In":[28],"this":[29],"work,":[30],"we":[31],"consider":[32],"a":[33,75,86],"metric":[34,82],"measuring":[35,45],"semantic":[36,112],"similarities":[37,56],"captions":[42,58,102],"instead":[43],"exact":[46],"word":[47],"overlap.":[48],"We":[49,72],"first":[50],"evaluate":[51],"its":[52],"ability":[53],"to":[54,60,68,78],"capture":[55],"among":[57],"corresponding":[59],"same":[62],"audio":[63,91],"file":[64],"compare":[66],"it":[67],"other":[69],"established":[70],"metrics.":[71],"then":[73],"propose":[74],"fine-tuning":[76,95],"method":[77],"directly":[79],"optimize":[80],"by":[83,105],"backpropagating":[84],"through":[85],"sentence":[87],"embedding":[88],"extractor":[89],"network.":[93],"Such":[94],"results":[96],"in":[97,100],"an":[98],"improvement":[99],"as":[103],"measured":[104],"both":[106],"traditional":[107],"proposed":[111],"similarity":[113],"metric.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}