{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:02:44Z","timestamp":1776880964601,"version":"3.51.2"},"reference-count":31,"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\/icasspw65056.2025.11011255","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":1,"title":["TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification"],"prefix":"10.1109","author":[{"given":"Nishit","family":"Anand","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashish","family":"Seth","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramani","family":"Duraiswami","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853981"},{"key":"ref2","article-title":"Mridangam stroke dataset (1.0)","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Anantapadmanabhan"},{"key":"ref3","article-title":"Mridangam stroke dataset (1.0)","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Anantapadmanabhan"},{"key":"ref4","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref5","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979822"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref9","article-title":"Tut acoustic scenes 2017, development dataset","author":"Mesaros","year":"2017b","journal-title":"Data set"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref11","article-title":"Sound events for surveillance applications (1.0.0)","author":"Spadini","year":"2019","journal-title":"Data set"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref13","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref16","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref20","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024"},{"key":"ref21","article-title":"Compa: Addressing the gap in compositional reasoning in audio-language models","author":"Ghosh","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3318015"},{"key":"ref24","article-title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1082"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref28","article-title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","author":"Bai","year":"2024"},{"key":"ref29","article-title":"Efficient multimodal large language models: A survey","author":"Jin","year":"2024"},{"key":"ref30","article-title":"Grounding Multimodal Large Language Models in Actions","author":"Szot","year":"2024"},{"key":"ref31","article-title":"A Review of Multi-Modal Large Language and Vision Models","author":"Carolan","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"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\/11011255.pdf?arnumber=11011255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:54:46Z","timestamp":1748408086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11011255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icasspw65056.2025.11011255","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}