{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:37:15Z","timestamp":1774975035907,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,4]]},"DOI":"10.1145\/3636534.3697460","type":"proceedings-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T23:13:18Z","timestamp":1733353998000},"page":"1686-1688","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["TraMSR: Transformer and Mamba based Practical Speech Super-Resolution for Mobile Wearables"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1602-5359","authenticated-orcid":false,"given":"Yueyuan","family":"Sui","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1999-0078","authenticated-orcid":false,"given":"Minghui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Columbia University, New York, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7356-1348","authenticated-orcid":false,"given":"Junxi","family":"Xia","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6480-0299","authenticated-orcid":false,"given":"Xiaofan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Columbia University, New York, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5713-8885","authenticated-orcid":false,"given":"Stephen","family":"Xia","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Pang Wei W Koh, and Stefano Ermon","author":"Birnbaum Sawyer","year":"2019","unstructured":"Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei W Koh, and Stefano Ermon. 2019. Temporal FiLM: Capturing long-range sequence dependencies with feature-wise modulations. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847","author":"Defossez Alexandre","year":"2020","unstructured":"Alexandre Defossez, Gabriel Synnaeve, and Yossi Adi. 2020. Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847 (2020)."},{"key":"e_1_3_2_1_3_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher R\u00e9. 2021. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems 34","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher R\u00e9. 2021. Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems 34 (2021), 572--585."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23010035"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"e_1_3_2_1_8_1","volume-title":"Jose A Gonzalez, and Antonio M Peinado.","author":"Martin-Donas Juan Manuel","year":"2018","unstructured":"Juan Manuel Martin-Donas, Angel Manuel Gomez, Jose A Gonzalez, and Antonio M Peinado. 2018. A deep learning loss function based on the perceptual evaluation of the speech quality. IEEE Signal processing letters 25, 11 (2018), 1680--1684."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747699"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596082"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_1_13_1","volume-title":"TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platforms. arXiv preprint arXiv:2405.01242","author":"Sui Yueyuan","year":"2024","unstructured":"Yueyuan Sui, Minghui Zhao, Junxi Xia, Xiaofan Jiang, and Stephen Xia. 2024. TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platforms. arXiv preprint arXiv:2405.01242 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Junichi Yamagishi Christophe Veaux and Kirsten MacDonald. 2019. CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit. 10.7488\/ds\/2645","DOI":"10.7488\/ds\/2645"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"}],"event":{"name":"ACM MobiCom '24: 30th Annual International Conference on Mobile Computing and Networking","location":"Washington D.C. DC USA","acronym":"ACM MobiCom '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 30th Annual International Conference on Mobile Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3697460","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3636534.3697460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:59Z","timestamp":1750295399000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3697460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"references-count":16,"alternative-id":["10.1145\/3636534.3697460","10.1145\/3636534"],"URL":"https:\/\/doi.org\/10.1145\/3636534.3697460","relation":{},"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"2024-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}