EERA-ASR: An Energy-Efficient Reconfigurable Architecture for Automatic Speech Recognition With Hybrid DNN and Approximate Computing

Bo Liu, Yu Gong, Wei Ge, Mengwen Xia, Longxing Shi

IEEE Access · 2018 · 44 citations · 20 references

DOIFull text

Open access

Concepts

Abstract

This paper proposes a hybrid deep neural network (DNN) for automatic speech recognition and an energy-efficient reconfigurable architecture with approximate computing for accelerating the DNN. To accelerate the hybrid DNN and reduce the energy consumption, we propose a digital-analog mixed reconfigurable architecture with approximate computing units, including a binary weight network accelerator with analog multi-chain delay-addition units for bit-wise approximate computing and a recurrent neural network accelerator with approximate multiplication units for different calculation accuracy requirements. Implemented under TSMC 28nm HPC+ process technology, the proposed architecture can achieve the energy efficiency of 163.8TOPS/W for 20 keywords recognition and 3.3TOPS/W for common speech recognition.

References

20