{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:49:27Z","timestamp":1730231367663,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10626117","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"555-559","source":"Crossref","is-referenced-by-count":0,"title":["Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency"],"prefix":"10.1109","author":[{"given":"Sungho","family":"Jeon","sequence":"first","affiliation":[{"name":"Heidelberg Institute of Theoretical Studies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Feng","family":"Yeh","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakan","family":"Inan","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rashi","family":"Rungta","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashar","family":"Mehdad","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Bikel","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747432"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10584"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref5","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","author":"Kim","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Generating long sequences with sparse transformers","year":"2019","author":"Child","key":"ref6"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"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"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","volume-title":"NeuRIPS Workshop on Self-Supervised Learning for Speech and Audio Processing","author":"Zhang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref12","article-title":"Binarized neural networks","volume":"29","author":"Hubara","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Bit: Robustly binarized multi-distilled transformer","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Efficient speech representation learning with low-bit quantization","year":"2022","author":"Yeh","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref17","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","volume":"33","author":"Baalen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11313"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626117.pdf?arnumber=10626117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:51:14Z","timestamp":1723787474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626117","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}