audio-10

Packet Loss Concealment

3260 papers • 126 benchmarks • 313 datasets

Predicting audio packets lost during transmission.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in packet-loss-concealment-21

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find packet-loss-concealment-21 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels

Ivan V. Baji'c, Ashiv Dhondea, R. Cohen•Tue Nov 30 2021

A simulation framework called DFTS2 is presented, which enables researchers to define the components of the CI system in TensorFlow~2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies.

0

Content

0

Paper Graph

Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model

Paris Smaragdis, Ahmed Mustafa, J. Valin, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil, A. Krishnaswamy•Tue May 10 2022

A hybrid neural PLC architecture where the missing speech is synthesized using a generative model conditioned using a predictive model to achieve natural concealment that surpasses the quality of existing conventional PLC algorithms and ranked second in the Interspeech 2022 PLC Challenge.

24 0

Paper Graph

tPLCnet: Real-time Deep Packet Loss Concealment in the Time Domain Using a Short Temporal Context

Nils L. Westhausen, B. Meyer•Sun Apr 03 2022

A real-time time-domain packet loss concealment (PLC) neural-network (tPLCnet) that efficiently predicts lost frames from a short context buffer in a sequence-to-one (seq2one) fashion.

10 0

Paper Graph

A Time-Frequency Generative Adversarial Based Method for Audio Packet Loss Concealment

Samuele Cornell, S. Squartini, Carlo Aironi, L. Serafini•Thu Jul 27 2023

This paper introduces the combination of two STFT-based loss functions, mixed with the traditional GAN objective, and employs a modified PatchGAN structure as discriminator and lower the concealment time by a proper initialization of the phase reconstruction algorithm.

13 0

Paper Graph

Adding a benchmark result helps the community track progress.