.png){kind=icon}
.png){kind=icon}
Return
More is Less: Domain-Specific Speech Recognition Microprocessor Using One-Dimensional Convolutional Recurrent Neural Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSI.2021.3134271.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Low-power keywords recognition has been a focus of acoustic signal processing for several decades. This work investigates the domain-specific speech recognition microprocessor based on optimized one-dimensional convolutional recurrent neural network (1D-CRNN). Compared to previous DNN based frameworks, the proposed 1D-CRNN can process both the feature extraction and keywords classification, and achieve high recognition accuracy with reduced computation operations under wide range background noise SNRs. An energyefficient 1D-CRNN accelerator is implemented to dynamically reconfigure and process the different layers. This accelerator has the characteristics of More is Less in three aspects: 1) the hybrid network with more complex layers is much more compact and requires less computation; 2) although the weight width quantized to 8 bits requires more memory size and multiplication energy cost, the required network neurons can be reduced and hardware utilization can he improved; 3) an energy-aware self-compensation tensor multiplication unit with dual power supply based on approximation design method can be utilized for 1D-CRNN computing. Compared to the state-of-the-art architectures, the novel more-is-less architecture can achieve a much lower power consumption of 1.4 mu W similar to 2.1 mu W (over 80% reduced) under an industry 22nm technology, while maintaining higher system adaptability (support SNRs: -5dB similar to Clean) for 1 similar to 5 real-time keywords recognition.
Keywords:
Acoustic signal processing
neural network
keywords classification
approximate computing
Journal
IF:
5.2
Papers:
9.7K
Citations:
2.2W