{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:35:36Z","timestamp":1790703336331,"version":"4.1.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832169","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1015-1022","source":"Crossref","is-referenced-by-count":7,"title":["DASS: Distilled Audio State Space Models are Stronger and More Duration-Scalable Learners"],"prefix":"10.1109","author":[{"given":"Saurabhchand","family":"Bhati","sequence":"first","affiliation":[{"name":"MIT,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gong","sequence":"additional","affiliation":[{"name":"MIT,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonid","family":"Karlinsky","sequence":"additional","affiliation":[{"name":"IBM Research AI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rogerio","family":"Feris","sequence":"additional","affiliation":[{"name":"IBM Research AI,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[{"name":"MIT,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","volume":"30","author":"Shazeer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref4","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref9","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref12","first-page":"100","article-title":"Convolution-augmented transformer for semisupervised sound event detection","volume-title":"Proc. workshop detection classification Acoust. Scenes events (DCASE)","author":"Miyazaki"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3014737"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref15","article-title":"Audio mamba: Pretrained audio state space model for audio tagging","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2405.13636"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832304"},{"key":"ref17","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv:2111.00396"},{"key":"ref18","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref19","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv preprint arXiv:2206.13947"},{"key":"ref20","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv:2401.09417"},{"key":"ref21","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2401.10166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1084"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"Cmkd: Cnn\/transformer-based crossmodel knowledge distillation for audio classification","author":"Gong","year":"2022","journal-title":"arXiv preprint arXiv:2203.06760"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832169.pdf?arnumber=10832169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:06Z","timestamp":1737101286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832169","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}