Current Trends in Joint Audio-Video Signal Processing: A Review

Abstract

Multimodal signal processing has gained a lot of significance in recent years due to advances in computer technology as well as more sophisticated sensors being available. One example is the joint processing of audio and video signals in a variety of applications. This paper serves as a broad introduction to the special session on "Audio-Video Signal Processing and its Applications". The paper reviews current trends and developments in joint audio-video (AV) signal processing and gives an overview of current issues in theory and application in this area. We focus on speech processing, person authentication, and affective sensing as examples. An overview of available AV data corpora is given.