Real-Time Audio Quality Evaluation for Adaptive Multimedia Protocols

The quality of audio in IP telephony is significantly influenced by the impact of packet loss rate, burstiness and distribution on a specific audio compression technique. In this paper, we propose a novel statistical-based on-line audio quality assessment framework, Audio Genome, that can deduce the audio quality of an on-going Internet audio for many different codecs under any network loss condition at real-time. Our approach is superior to proposed learning-based techniques in terms of computational speed and ease of deployment. Our extensive evaluation experiments, that include large simulation scenarios, show that our approach is accurate and viable for adaptive real-time audio mechanisms. Finally, we show a deployment of Audio Genome as an integral part of an adaptive rate control mechanism.