Name
Title | ||
|---|---|---|
UltraTrail: A Configurable Ultralow-Power TC-ResNet AI Accelerator for Efficient Keyword Spotting |
Abstract | ||
|---|---|---|
Recent advances in machine learning show the superior behavior of temporal convolutional networks (TCNs) and especially their combination with residual networks (TC-ResNet) for intelligent sensor signal processing in comparison to classical CNNs and LSTMs. In this article, we propose UltraTrail, a configurable, ultralow-power TC-ResNet AI accelerator for sensor signal processing and its application to efficient keyword spotting (KWS). Following a strict hardware/model co-design approach, we have derived an optimized low-power hardware architecture for generalized TC-ResNet topologies consisting of a configurable array of processing elements and a distributed memory with dynamic content reallocation. We additionally extend the network with conditional computing to reduce the number of operations during inference and to provide the possibility for power-gating. The final accelerator implementation in Globalfoundries' 22FDX technology achieves a power consumption of 8.2 μW for the task of always-on KWS meeting the real-time requirement of 100 ms per inference with an accuracy of 93% on the Google Speech Command Dataset. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/TCAD.2020.3012320 | IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems |
Keywords | DocType | Volume |
Accelerator architectures,deep neural networks (DNNs),edge computing,low-power electronics,neural network hardware | Journal | 39 |
Issue | ISSN | Citations |
11 | 0278-0070 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Paul Palomero Bernardo | 1 | 0 | 1.01 |
| Christoph Gerum | 2 | 0 | 1.35 |
| Adrian Frischknecht | 3 | 0 | 1.35 |
| Konstantin Lübeck | 4 | 0 | 0.34 |
| Oliver Bringmann | 5 | 586 | 71.36 |