Energy-Efficient Speaker Identification with Low-Precision Networks
Name
sid-ternary-nets.pdf
Description
Accepted version
Size
184.98 KB
Format
Adobe PDF
Checksum (MD5)
a67d14b2a91f79b0e1928e72f011e403
Author(s)
Koppula, Skanda K.
Glass, James R
Chandrakasan, Anantha P
Date Issued
September 2018
Journal
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Koppula, Skanda et al. "Energy-Efficient Speaker Identification with Low-Precision Networks." 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2018, Calgary, AB, Canada, Institute of Electrical and Electronics Engineers (IEEE), September 2018. © 2018 IEEE
Version
Author's final manuscript
Abstract
Power-consumption in small devices is dominated by off-chip memory accesses, necessitating small models that can fit in on-chip memory. In the task of text-dependent speaker identification, we demonstrate a 16x byte-size reduction for state-of-art small-footprint LCN/CNN/DNN speaker identification models. We achieve this by using ternary quantization that constrains the weights to {-1, 0, 1}. Our model comfortably fits in the 1 MB on-chip BRAM of most off-the-shelf FPGAs, allowing for a power-efficient speaker ID implementation with 100x fewer floating point multiplications, and a 1000x decrease in estimated energy cost. Additionally, we explore the use of depth-wise separable convolutions for speaker identification, and show while significantly reducing multiplications in full-precision networks, they perform poorly when ternarized. We simulate hardware designs for inference on our model, the first hardware design targeted for efficient evaluation of ternary networks and end-to-end neural network-based speaker identification.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/icassp.2018.8462498
