{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:10:34Z","timestamp":1776888634974,"version":"3.51.2"},"reference-count":30,"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\/icassp49660.2025.10888123","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds"],"prefix":"10.1109","author":[{"given":"Sreyan","family":"Ghosh","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonal","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chandra Kiran Reddy","family":"Evuru","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oriol","family":"Nieto","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramani","family":"Duraiswami","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"Adobe Research,San Francisco,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref2","article-title":"Compa: Addressing the gap in compositional reasoning in audio-language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ghosh"},{"key":"ref3","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023"},{"key":"ref4","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448030"},{"key":"ref6","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref7","article-title":"CoLLAT: On adding fine-grained audio understanding to language models using token-level locked-language tuning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Silva"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888245"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref15","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023"},{"key":"ref16","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref17","article-title":"Listen, think, and understand","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gong"},{"key":"ref18","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref21","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International Conference on Machine Learning","author":"Engel"},{"key":"ref22","article-title":"A multi-device dataset for urban acoustic scene classification","author":"Mesaros","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"issue":"140","key":"ref25","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP43922.2022.9746312","article-title":"Hts-at: A hierarchical token-semantic audio transformer for sound classification and detection","volume-title":"ICASSP 2022","author":"Chen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888123.pdf?arnumber=10888123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:48Z","timestamp":1774416408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888123\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888123","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}