Adaptive Voice Smoothing with Optimal Playback Delay Based on the ITU-T E-Model

Perceived voice quality is mainly affected by IP network impairments such as delay, jitter and packet loss. Adaptive smoothing buffer at the receiving end can compensate for the effects of jitter based on a tradeoff between delay and loss to archive a best voice quality. This work formulates an online loss model which incorporates buffer sizes and applies the ITU-T E-model approach to optimize the delay-loss problem. Distinct from the other optimal smoothers, the proposed optimal smoother suitable for most of codecs carries the lowest complexity. Since the adaptive smoothing scheme introduces variable playback delays, the buffer re-synchronization between the capture and the playback becomes essential. This work also presents a buffer re-synchronization algorithm based on silence skipping to prevent unacceptable increase in the buffer preloading delay and even buffer overflow. Simulation experiments validate that the proposed adaptive smoother archives significant improvement in the voice quality.