Title | ||
---|---|---|
NS-FDN: Near-Sensor Processing Architecture of Feature-Configurable Distributed Network for Beyond-Real-Time Always-on Keyword Spotting |
Abstract | ||
---|---|---|
Always-on keyword spotting (KWS) that detects wake-up words has been the indispensable module in the voice interaction system. However, the ultra-low-power embedded devices put forward strict requirements on energy consumption, latency, and recognition accuracy of KWS. In this work, we propose a near-sensor processing architecture of feature-configurable distributed network (NS-FDN) for always-on ... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TCSI.2021.3059649 | IEEE Transactions on Circuits and Systems I: Regular Papers |
Keywords | DocType | Volume |
Feature extraction,Power demand,Artificial neural networks,Speech recognition,Hardware,Energy consumption,Microphones | Journal | 68 |
Issue | ISSN | Citations |
5 | 1549-8328 | 2 |
PageRank | References | Authors |
0.39 | 0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qin Li | 1 | 2 | 1.40 |
Changlu Liu | 2 | 2 | 1.40 |
Dong Peiyan | 3 | 4 | 3.12 |
Yanming Zhang | 4 | 2 | 0.73 |
Tong Li | 5 | 3 | 0.74 |
Sheng Lin | 6 | 2 | 0.39 |
Minda Yang | 7 | 2 | 0.39 |
Fei Qiao | 8 | 94 | 35.38 |
Yanzhi Wang | 9 | 1082 | 136.11 |
Li Luo | 10 | 5 | 2.89 |
Huazhong Yang | 11 | 2239 | 214.90 |