Name
Title | ||
|---|---|---|
AAD-KWS: a sub-µW keyword spotting chip with a zero-cost, acoustic activity detector from a 170nW MFCC feature extractor in 28nm CMOS |
Abstract | ||
|---|---|---|
As a widely used speech-triggered interface, deep-learning based keyword spotting (KWS) chips require both ultra-low power and high detection accuracy. We propose an always-on keyword spotting chip with an acoustic activity detection (AAD) to achieve the above two requirements. Extracted from feature extractor, this AAD has zero overhead and zero miss rate. It is used to clock gate the neural netw... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ESSCIRC53450.2021.9567770 | ESSCIRC 2021 - IEEE 47th European Solid State Circuits Conference (ESSCIRC) |
Keywords | DocType | ISSN |
Power demand,Voltage,Detectors,Artificial neural networks,Logic gates,Feature extraction,Acoustics | Conference | 1930-8833 |
ISBN | Citations | PageRank |
978-1-6654-3751-6 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lixuan Zhu | 1 | 0 | 0.34 |
| Weiwei Shan | 2 | 22 | 12.51 |
| Jiaming Xu | 3 | 0 | 0.34 |
| Yi-Cheng Lu | 4 | 5 | 2.23 |