{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:01:46Z","timestamp":1748491306477,"version":"3.41.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icasspw65056.2025.11011270","type":"proceedings-article","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:05:14Z","timestamp":1748365514000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["MACE: Leveraging Audio for Evaluating Audio Captioning Systems"],"prefix":"10.1109","author":[{"given":"Satvik","family":"Dixit","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Soham","family":"Deshmukh","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref4","first-page":"18090","article-title":"Pengi: An audio language model for audio tasks","volume":"36","author":"Deshmukh","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref6","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out.","author":"Lin","year":"2004"},{"key":"ref7","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.729"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448154"},{"article-title":"Investigations in audio captioning: Addressing vocabulary imbalance and evaluating suitability of language-centric performance metrics","year":"2023","author":"Kothinti","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref21"},{"key":"ref22","first-page":"7881","article-title":"BLEURT: Learning robust metrics for text generation","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Sellam"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289793"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref24"},{"article-title":"Clair-a: Leveraging large language models to judge audio captions","year":"2024","author":"Wu","key":"ref25"},{"article-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"issue":"8","key":"ref30","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-325"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"article-title":"Vision language models are few-shot audio spectrogram classifiers","volume-title":"Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation","author":"Dixit","key":"ref35"},{"article-title":"A closer look at weak label learning for audio events","year":"2018","author":"Shah","key":"ref36"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2025,4,6]]},"location":"Hyderabad, India","end":{"date-parts":[[2025,4,11]]}},"container-title":["2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11010992\/11010997\/11011270.pdf?arnumber=11011270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:55:01Z","timestamp":1748408101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011270","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}