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

2021-09-11 · Abhishek Ramdas Nair, Shantanu Chakrabartty, Chetan Singh Thakur

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.

📄 PDF Abstract BibTeX arXiv:2109.06171

Code (0)

등록된 구현이 없습니다.

Tasks

Robust classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Ultrasound Detection Arrays Via Coded Hadamard Apertures

2020-02-27 · Evgeny Hahamovich, Amir Rosenthal

In the medical fields, ultrasound detection is often performed with piezoelectric arrays that enable one to simultaneously map the acoustic fields at several positions. In this work, we develop a novel method for transfo…

GPAIR: Gaussian-Kernel-Based Ultrafast 3D Photoacoustic Iterative Reconstruction

2026-02-03 · Yibing Wang, Shuang Li, Tingting Huang, Yu Zhang 외 arxiv

Although the iterative reconstruction (IR) algorithm can substantially correct reconstruction artifacts in photoacoustic (PA) computed tomography (PACT), it suffers from long reconstruction times, especially for large-sc…

Image Reconstruction

Acoustic neural networks: Identifying design principles and exploring physical feasibility

2025-11-26 · Ivan Kalthoff, Marcel Rey, Raphael Wittkowski arxiv

Wave-guide-based physical systems provide a promising route toward energy-efficient analog computing beyond traditional electronics. Within this landscape, acoustic neural networks represent a promising approach for achi…

Learning Filter Banks Using Deep Learning For Acoustic Signals

2016-11-29 · Shuhui Qu, Juncheng Li, Wei Dai, Samarjit Das

Designing appropriate features for acoustic event recognition tasks is an active field of research. Expressive features should both improve the performance of the tasks and also be interpret-able. Currently, heuristicall…

Deep Learning

Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping

2020-11-05 · Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh, Gerhard Widmer

Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limited resource budget, designing low-compl…

Acoustic Scene Classification Scene Classification