{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:54Z","timestamp":1776888414145,"version":"3.51.2"},"reference-count":20,"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\/icassp49660.2025.10889317","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Feature Audio Fusion for Nonverbal Vocalization Classification"],"prefix":"10.1109","author":[{"given":"Siddhant Bikram","family":"Shah","sequence":"first","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kristina T.","family":"Johnson","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering Department of Communication Sciences and Disorders,Boston,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076364"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101869"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app11041890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3398584"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02405-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446253"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","author":"Shah","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Rethinking cnn models for audio classification","author":"Palanisamy","year":"2020"},{"key":"ref15","article-title":"Pooling methods in deep neural networks, a review","author":"Gholamalinezhad","year":"2020"},{"key":"ref16","article-title":"Long-tail learning with foundation model: Heavy fine-tuning hurts","volume-title":"Forty-first International Conference on Machine Learning","author":"Shi"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.13053\/cys-18-3-2043"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACII55700.2022.9953820"}],"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\/10889317.pdf?arnumber=10889317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:50Z","timestamp":1774416290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889317","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}