English

In-filter Computing For Designing Ultra-light Acoustic Pattern Recognizers

Audio and Speech Processing 2021-09-15 v1 Machine Learning Neural and Evolutionary Computing Sound Systems and Control Systems and Control

Abstract

We present a novel in-filter computing framework that can be used for designing ultra-light acoustic classifiers for use in smart internet-of-things (IoTs). Unlike a conventional acoustic pattern recognizer, where the feature extraction and classification are designed independently, the proposed architecture integrates the convolution and nonlinear filtering operations directly into the kernels of a Support Vector Machine (SVM). The result of this integration is a template-based SVM whose memory and computational footprint (training and inference) is light enough to be implemented on an FPGA-based IoT platform. While the proposed in-filter computing framework is general enough, in this paper, we demonstrate this concept using a Cascade of Asymmetric Resonator with Inner Hair Cells (CAR-IHC) based acoustic feature extraction algorithm. The complete system has been optimized using time-multiplexing and parallel-pipeline techniques for a Xilinx Spartan 7 series Field Programmable Gate Array (FPGA). We show that the system can achieve robust classification performance on benchmark sound recognition tasks using only ~ 1.5k Look-Up Tables (LUTs) and ~ 2.8k Flip-Flops (FFs), a significant improvement over other approaches.

Keywords

Cite

@article{arxiv.2109.06171,
  title  = {In-filter Computing For Designing Ultra-light Acoustic Pattern Recognizers},
  author = {Abhishek Ramdas Nair and Shantanu Chakrabartty and Chetan Singh Thakur},
  journal= {arXiv preprint arXiv:2109.06171},
  year   = {2021}
}

Comments

in IEEE Internet of Things Journal

R2 v1 2026-06-24T05:55:44.770Z