A 1D-CRNN Inspired Reconfigurable Processor for Noise-robust Low-power Keywords Recognition
Bo Liua, Zeyu Shenb, Lepeng Huangc, Yu Gongd, Zilong Zhange and Hao Caif
National ASIC System Engineering Research Center, Southeast University, Nanjing, China
aliubo cnasic@seu.edu.cn
bzeyushen@seu.edu.cn
chuanglepeng@seu.edu.cn
dgongyu@seu.edu.cn
ezhangzilong@seu.edu.cn
fhao.cai@seu.edu.cn
ABSTRACT
A low-power high-accuracy reconfigurable processor is proposed for noise-robust keywords recognition and evaluated in 22nm technology, which is based on an optimized one-dimensional convolutional recurrent neural network (1D-CRNN). In traditional DNN-based keywords recognition system, the speech feature extraction based on traditional algorithms and the DNN based keywords classification are two independent modules. Compared to the traditional architecture, both the feature extraction and keywords classification are processed by the proposed 1D-CRNN with weight/data bit width quantized to 8/8 bits. Therefore unified training and optimization framework can be performed for various application scenarios and input loads. The proposed 1D-CRNN based keywords recognition system can achieve a higher recognition accuracy with reduced computation operations. Based on system-architecture co-design, an energy-efficient DNN accelerator which can be dynamically reconfigured to process the 1D-CRNN with different configurations is proposed. The processing circuits of the accelerator are optimized to further improve the energy efficiency using a fine-grained precision reconfigurable approximate multiplier. Compared to the state-of-theart architectures, this work can support 1∼5 real-time keywords recognition with lower power consumption, while maintaining higher system capability and adaptability.
Keywords: Noise-Robust Keywords Recognition, Feature Extraction, Precision Eeconfigurable, Approximate Multiplier.
