Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
REAL-TIME PACKET LOSS CONCEALMENT USING DEEP GENERATIVE NETWORKS
Document Type and Number:
WIPO Patent Application WO/2022/079164
Kind Code:
A3
Abstract:
The present disclosure relates to a method and system for performing packet loss concealment using a neural network system. The method comprises obtaining a representation of an incomplete audio signal, inputting the representation of the incomplete audio signal to an encoder neural network and outputting a latent representation of a predicted complete audio signal. The latent representation is input to a decoder neural network which outputs a representation of a predicted complete audio signal comprising a reconstruction of the original portion of the complete audio signal, wherein said encoder neural network and said decoder neural network have been trained with an adversarial neural network.

Inventors:
PASCUAL SANTIAGO (ES)
SERRA JOAN (ES)
PONS PUIG JORDI (ES)
Application Number:
PCT/EP2021/078443
Publication Date:
June 02, 2022
Filing Date:
October 14, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
DOLBY INT AB (NL)
International Classes:
G10L19/005; G10L19/00
Other References:
ANDRES MARAFIOTI ET AL: "GACELA -- A generative adversarial context encoder for long audio inpainting", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 11 May 2020 (2020-05-11), XP081929700, DOI: 10.1109/JSTSP.2020.3037506
MOSTAFA M MOHAMED ET AL: "On Deep Speech Packet Loss Concealment: A Mini-Survey", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 15 May 2020 (2020-05-15), XP081674545
OORD AARON ET AL: "Neural Discrete Representation Learning", 30 May 2018 (2018-05-30), XP055845398, Retrieved from the Internet [retrieved on 20210928]
Attorney, Agent or Firm:
DOLBY INTERNATIONAL AB PATENT GROUP EUROPE (NL)
Download PDF: