A 3.8-μW 10-Keyword Noise-Robust Keyword Spotting Processor Using Symmetric Compressed Ternary-Weight Neural Networks
In: IEEE Open Journal of the Solid-State Circuits Society, Jg. 3 (2023), S. 185-196
Online
academicJournal
Zugriff:
A ternary-weight neural network (TWN) inspired keyword spotting (KWS) processor is proposed to support complicated and variable application scenarios. To achieve high-precision recognition of ten keywords under 5 dB~Clean wide range of background noises, a convolution neural network consists of four convolution layers and four fully connected layers, with modified sparsity-controllable truncated Gaussian approximation-based ternary-weight training is used. End-to-end optimization composed of three techniques is utilized: 1) the stage-by-stage bit-width selection algorithm to optimize the hardware overhead of FFT; 2) the lossy compressed TWN with symmetric kernel training (SKT) and dedicated internal data reuse computation flow; and 3) the error intercompensation approximate addition tree to reduce the computation overhead with marginal accuracy loss. Fabricated in an industrial 22-nm CMOS process, the processor realizes up to ten keywords in real-time recognition under 11 background noise types, with the accuracy of 90.6%@clean and 85.4%@5 dB. It consumes an average power of $3.8 ~\mu \text{W}$ at 250 kHz and the normalized energy efficiency is $2.79\times $ higher than state of the art.
Titel: |
A 3.8-μW 10-Keyword Noise-Robust Keyword Spotting Processor Using Symmetric Compressed Ternary-Weight Neural Networks
|
---|---|
Autor/in / Beteiligte Person: | Liu, Bo ; Xie, Na ; Zhang, Renyuan ; Yang, Haichuan ; Wang, Ziyu ; Fan, Deliang ; Wang, Zhen ; Liu, Weiqiang ; Cai, Hao |
Link: | |
Zeitschrift: | IEEE Open Journal of the Solid-State Circuits Society, Jg. 3 (2023), S. 185-196 |
Veröffentlichung: | IEEE, 2023 |
Medientyp: | academicJournal |
ISSN: | 2644-1349 (print) |
DOI: | 10.1109/OJSSCS.2023.3312354 |
Schlagwort: |
|
Sonstiges: |
|