A packet loss recovery of G.729 speech using discriminative model and N-gram

Takeshi Nagano, Akinori Ito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In a VoIP application, packet losses degrade speech quality. Especially, IP network under a large-scale disaster should cause severe packet losses. We have investigated the relationship between parameter loss and speech quality for G.729 codec. In this paper, we propose packet loss recovery method under severe packet loss condition, where the relationship was modeled by Support Vector Machine (SVM). Compared with the 'repetition' method, the proposed method could improve speech quality. When we used both SVM and N-gram for concealing packet losses, we could obtain further improvement of speech quality.

Original languageEnglish
Title of host publicationProceedings - 2013 9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2013
PublisherIEEE Computer Society
Pages267-270
Number of pages4
ISBN (Print)9780769551203
DOIs
Publication statusPublished - 2013 Jan 1
Event9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2013 - Beijing, China
Duration: 2013 Oct 162013 Oct 18

Publication series

NameProceedings - 2013 9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2013

Other

Other9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2013
CountryChina
CityBeijing
Period13/10/1613/10/18

Keywords

  • G.729
  • N-gram
  • SVM
  • packet loss recovery

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'A packet loss recovery of G.729 speech using discriminative model and N-gram'. Together they form a unique fingerprint.

Cite this