Improving performance of real-time full-band blind packet-loss concealment with predictive network

Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong

Submitted on 8 November 2022, last revised on 10 November 2022


Packet loss concealment (PLC) is a tool for enhancing speech degradation caused by poor network conditions or underflow/overflow in audio processing pipelines. We propose a real-time recurrent method that leverages previous outputs to mitigate artefact of lost packets without the prior knowledge of loss mask. The proposed full-band recurrent network (FRN) model operates at 48 kHz, which is suitable for high-quality telecommunication applications. Experiment results highlight the superiority of FRN over an offline non-causal baseline and a top performer in a recent PLC challenge.


Comment: Submitted to ICASSP 2023, 5 pages, 1 figure, 4 tables

Subjects: Computer Science - Sound; Electrical Engineering and Systems Science - Audio and Speech Processing