Details
Poster
Presenter(s)
![Bo Liu Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/10491.jpg?h=8f391919&itok=SUwVcNu_)
Display Name
Bo Liu
- Affiliation
-
AffiliationSoutheast University
- Country
Abstract
In this paper, an ultra-low power speech recognition processor is implemented based on an optimized binarized weight neural-network (BWN). To accelerate the BWN and make it energy efficient, we proposed an approximate computing architecture for the quantized BWN based on time-domain digital-analog mixed addition unit and precision optimization with fault-tolerant training method. Experimental results show that the proposed digital-analog mixed approximate computing architecture can significantly reduce the power consumption while maintaining the recognition accuracy. Implemented under TSMC 28nm, the proposed processor can support 10 keywords real time recognition under different noise types and SNRs, while the power consumption is 56uW.