A Survey on Probabilistic Models in Human Perception and Machines.

Lux Li,Robert Rehr,Patrick Bruns,Brigitte Röder,Timo Gerkmann

doi:10.3389/frobt.2020.00085

Abstract

Extracting information from noisy signals is of fundamental importance for both biological and artificial perceptual systems. To provide tractable solutions to this challenge, the fields of human perception and machine signal processing (SP) have developed powerful computational models, including Bayesian probabilistic models. However, little true integration between these fields exists in their applications of the probabilistic models for solving analogous problems, such as noise reduction, signal enhancement, and source separation. In this mini review, we briefly introduce and compare selective applications of probabilistic models in machine SP and human psychophysics. We focus on audio and audio-visual processing, using examples of speech enhancement, automatic speech recognition, audio-visual cue integration, source separation, and causal inference to illustrate the basic principles of the probabilistic approach. Our goal is to identify commonalities between probabilistic models addressing brain processes and those aiming at building intelligent machines. These commonalities could constitute the closest points for interdisciplinary convergence.

Highlights

Human perception and machine signal processing (SP) both face the fundamental challenge of handling uncertainty
Causal inference models estimate the hidden source or causal structure of the inputs, by factoring in causality which is important for determining input integration or source separation
More advanced models, such as those in machine learning, are beyond the scope of this mini review

Summary

A Survey on Probabilistic Models in Human Perception and Machines

Edited by: Subhadeep Chakraborty, The University of Tennessee, Knoxville, United States. Little true integration between these fields exists in their applications of the probabilistic models for solving analogous problems, such as noise reduction, signal enhancement, and source separation. In this mini review, we briefly introduce and compare selective applications of probabilistic models in machine SP and human psychophysics. Our goal is to identify commonalities between probabilistic models addressing brain processes and those aiming at building intelligent machines. These commonalities could constitute the closest points for interdisciplinary convergence

INTRODUCTION

SUMMARY AND OUTLOOK

Limitations