{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:22Z","timestamp":1775199922040,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434686","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers"],"prefix":"10.1109","author":[{"given":"Tzu-Quan","family":"Lin","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}]},{"given":"Tsung-Huan","family":"Yang","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}]},{"given":"Chun-Yao","family":"Chang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles,United States"}]},{"given":"Kuang-Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Washington,United States"}]},{"given":"Tzu-Hsun","family":"Feng","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Edinburgh,United Kingdom"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","article-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","volume-title":"International Conference on Learning Representations","author":"Han"},{"key":"ref6","article-title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","author":"Emily","year":"2014","journal-title":"Advances in Neural Information Processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447928"},{"key":"ref13","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint arXiv:1910.01108"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"ref15","article-title":"Are Sixteen Heads Really Better than One?","volume":"32","author":"Michel","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Reducing Transformer Depth on Demand with Structured Dropout","volume-title":"International Conference on Learning Representations","author":"Fan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"ref18","first-page":"21256","article-title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","volume":"34","author":"Lai","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.14"},{"key":"ref20","article-title":"DistillW2V2: A Small and Streaming wav2vec 2.0 Based ASR Model","author":"Fu","year":"2023","journal-title":"arXiv preprint arXiv:2303.09278"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832151"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC65261.2025.11249191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-626"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389700"},{"key":"ref27","article-title":"Optimal Brain Damage","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Learning both Weights and Connections for Efficient Neural Network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","volume-title":"International Conference on Learning Representations","author":"Frankle"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref32","article-title":"Do Deep Nets Really Need to be Deep?","volume":"27","author":"Ba","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01604"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434686.pdf?arnumber=11434686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:19Z","timestamp":1775192299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434686","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}