Hu, J., Zhang, Z., Leow, C. S., Goh, W. L., & Gao, Y. (2024). Late Breaking Results: Circuit-Algorithm Co-design for Learnable Audio Analog Front-End. Proceedings of the 61st ACM/IEEE Design Automation Conference, 1–2. https://doi.org/10.1145/3649329.3663496
Abstract:
This paper presents a circuit-algorithm co-design framework for learnable audio analog front-end (AFE) which includes an analog filterbank for feature extraction and a classifier based on Depthwise Separable Convolutional Neural Network (DSCNN). Instead of the traditional approach to design the analog filterbank and digital classifier separately, a learnable filterbank is proposed and its source-follower bandpass filter (SF-BPF) parameters are optimized together with the neural network classifier in a signal-to-noise ratio (SNR)-aware training process. A new system criterion function (LBPF) is proposed to include classification loss and filter performance into the training process. The optimized audio AFE achieves 10.6% and 11.7% reduction in BPF power and chip area, respectively. Meanwhile, this approach achieved 88.6%–94.5% accuracy for 10-keyword classification task across a wide range of input signal SNR from 5dB to 20dB, with only 16k trainable parameters.
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR), Singapore - Nanosystems at the Edge programme
Grant Reference no. : A18A1b0055