Design and Analysis of Binary Scalar Quantizer of Laplacian Source with Applications

Zoran Peric,Vladimir Despotovic,Milan Savic,Bojan Denic

doi:10.3390/info11110501

Zoran Peric, Vladimir Despotovic + Show 2 more

Open Access

https://doi.org/10.3390/info11110501

Copy DOI

Abstract

A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented that investigate the effect of clipping with the aim of reducing the quantization noise, where the minimal mean-squared error distortion is used to determine the optimal clipping factor. A detailed comparison of both models is provided, and the performance evaluation in a wide dynamic range of input data variances is also performed. The observed binary scalar quantization models are applied in standard signal processing tasks, such as speech and image quantization, but also to quantization of neural network parameters. The motivation behind the binary quantization of neural network weights is the model compression by a factor of 32, which is crucial for implementation in mobile or embedded devices with limited memory and processing power. The experimental results follow well the theoretical models, confirming their applicability in real-world applications.

Highlights

Quantization can be classified into two categories: scalar and vector [1,2]
We we describe thespeech implementation ofoptimal a binary quantizer using two frame-wise adaptive techniques describe the implementation of a binary quantizer using two frame-wise adaptive techniques (i.e., (i.e., PCM (Pulse Code Modulation) and adaptive delta modulation (ADM))
This paper has addressed a binary scalar quantizer for data with a Laplacian probability density function (PDF), with applications in speech and image coding, as well as the compression of neural networks

Summary

Introduction

Quantization can be classified into two categories: scalar and vector [1,2]. The classification has been made based on whether only one sample is quantized at a time, using a fixed number of bits per sample (scalar quantization), or a number of samples is quantized at a time (vector quantization).The main advantage of scalar quantization is the reduced design complexity, which may be a crucial point in applications where processing delay is a critical parameter, such as speech coding. The binary quantizer is the simplest scalar quantization model, where each symbol is represented by only one bit. The main benefit achieved with this model concerns data compression, rather than achieved signal quality. A detailed analysis of binary quantization from the viewpoint of signal (data) processing by assuming known data distribution, including a design for the reference variance and performance analysis in a wide dynamic range of variances, is not available in the literature. This motivated the Information 2020, 11, 501; doi:10.3390/info11110501 www.mdpi.com/journal/information

Objectives

Methods

Findings

Conclusion