TMGAN-PLC: Audio Packet Loss Concealment using Temporal Memory Generative Adversarial Network

TL;DR

This paper introduces TMGAN-PLC, a novel generative adversarial network that leverages temporal memory and multi-stage quantization to improve real-time audio packet loss concealment, achieving higher speech quality and intelligibility.

Contribution

The paper presents a new TMGAN-PLC model with a nested-UNet generator and multi-stage quantizers, enhancing high-quality voice reconstruction with limited buffer sizes.

Findings

Improved speech quality and intelligibility in packet loss scenarios

Effective reconstruction of long burst losses

Promising results on the PLC Challenge dataset

Abstract

Real-time communications in packet-switched networks have become widely used in daily communication, while they inevitably suffer from network delays and data losses in constrained real-time conditions. To solve these problems, audio packet loss concealment (PLC) algorithms have been developed to mitigate voice transmission failures by reconstructing the lost information. Limited by the transmission latency and device memory, it is still intractable for PLC to accomplish high-quality voice reconstruction using a relatively small packet buffer. In this paper, we propose a temporal memory generative adversarial network for audio PLC, dubbed TMGAN-PLC, which is comprised of a novel nested-UNet generator and the time-domain/frequency-domain discriminators. Specifically, a combination of the nested-UNet and temporal feature-wise linear modulation is elaborately devised in the generator to finely adjust the intra-frame information and establish inter-frame temporal dependencies. To complement the missing speech content caused by longer loss bursts, we employ multi-stage gated vector quantizers to capture the correct content and reconstruct the near-real smooth audio. Extensive experiments on the PLC Challenge dataset demonstrate that the proposed method yields promising performance in terms of speech quality, intelligibility, and PLCMOS.