Soundsieve: Seconds-long audio event recognition on intermittently-powered systems

M Monjur, Y Luo, Z Wang, S Nirjon - Proceedings of the 21st Annual …, 2023 - dl.acm.org
A fundamental problem of every intermittently-powered sensing system is that signals
acquired by these systems over a longer period in time are also intermittent. As a …

An experimental study on private aggregation of teacher ensemble learning for end-to-end speech recognition

CHH Yang, IF Chen, A Stolcke… - 2022 IEEE Spoken …, 2023 - ieeexplore.ieee.org
Differential privacy (DP) is one data protection avenue to safeguard user information used
for training deep models by imposing noisy distortion on privacy data. Such a noise …

Intermittent-aware distributed concurrency control

WC Tsai, WM Chen, TW Kuo… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Internet of Things (IoT) devices are gradually adopting battery-less, energy harvesting
solutions, thereby driving the development of an intermittent computing paradigm to …

Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach

MK Elyaderani, S Shirani - arXiv preprint arXiv:2406.00901, 2024 - arxiv.org
The process of reconstructing missing parts of speech audio from context is called speech in-
painting. Human perception of speech is inherently multi-modal, involving both audio and …