On GMM Kalman predictive coding of LSFS for packet loss

Shaminda Subasingha, Manohar Murthi, Søren Vang Andersen

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

7 Citations (Scopus)

Abstract

Gaussian Mixture Model (GMM)-based Kalman predictive coders have been shown to perform better than baselineGMM Recursive Coders in predictive coding of Line Spectral Frequencies (LSFs) for both clean and packet loss conditions However, these stationary GMM Kalman predictive coders were not specifically designed for operation in packet loss conditions. In this paper, we demonstrate an approach to the the design of GMM-based predictive coding for packet loss channels. In particular, we show how a stationary GMM Kalman predictive coder can be modified to obtain a set of encoding and decoding modes, each with different Kalman gains. This approach leads to more robust performance of predictive coding of LSFs in packet loss conditions, as the coder mismatch between the encoder and decoder are minimized. Simulation results show that this Robust GMM Kalman predictive coder performs better than other baseline GMM predictive coders with no increase in complexity. To the best of our knowledge, no previous work has specifically examined the design of GMM predictive coders for packet loss conditions.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages4105-4108
Number of pages4
DOIs
StatePublished - Sep 23 2009
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China
Duration: Apr 19 2009Apr 24 2009

Other

Other2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
CountryTaiwan, Province of China
CityTaipei
Period4/19/094/24/09

Fingerprint

Packet loss
Decoding

Keywords

  • GMM
  • Kalman filtering
  • Speech coding
  • Vector quantization

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Subasingha, S., Murthi, M., & Andersen, S. V. (2009). On GMM Kalman predictive coding of LSFS for packet loss. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 4105-4108). [4960531] https://doi.org/10.1109/ICASSP.2009.4960531

On GMM Kalman predictive coding of LSFS for packet loss. / Subasingha, Shaminda; Murthi, Manohar; Andersen, Søren Vang.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 4105-4108 4960531.

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

Subasingha, S, Murthi, M & Andersen, SV 2009, On GMM Kalman predictive coding of LSFS for packet loss. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 4960531, pp. 4105-4108, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009, Taipei, Taiwan, Province of China, 4/19/09. https://doi.org/10.1109/ICASSP.2009.4960531
Subasingha S, Murthi M, Andersen SV. On GMM Kalman predictive coding of LSFS for packet loss. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. p. 4105-4108. 4960531 https://doi.org/10.1109/ICASSP.2009.4960531
Subasingha, Shaminda ; Murthi, Manohar ; Andersen, Søren Vang. / On GMM Kalman predictive coding of LSFS for packet loss. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2009. pp. 4105-4108
@inproceedings{66fad892317b4f08802af69edfdc95c9,
title = "On GMM Kalman predictive coding of LSFS for packet loss",
abstract = "Gaussian Mixture Model (GMM)-based Kalman predictive coders have been shown to perform better than baselineGMM Recursive Coders in predictive coding of Line Spectral Frequencies (LSFs) for both clean and packet loss conditions However, these stationary GMM Kalman predictive coders were not specifically designed for operation in packet loss conditions. In this paper, we demonstrate an approach to the the design of GMM-based predictive coding for packet loss channels. In particular, we show how a stationary GMM Kalman predictive coder can be modified to obtain a set of encoding and decoding modes, each with different Kalman gains. This approach leads to more robust performance of predictive coding of LSFs in packet loss conditions, as the coder mismatch between the encoder and decoder are minimized. Simulation results show that this Robust GMM Kalman predictive coder performs better than other baseline GMM predictive coders with no increase in complexity. To the best of our knowledge, no previous work has specifically examined the design of GMM predictive coders for packet loss conditions.",
keywords = "GMM, Kalman filtering, Speech coding, Vector quantization",
author = "Shaminda Subasingha and Manohar Murthi and Andersen, {S{\o}ren Vang}",
year = "2009",
month = "9",
day = "23",
doi = "10.1109/ICASSP.2009.4960531",
language = "English",
isbn = "9781424423545",
pages = "4105--4108",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - On GMM Kalman predictive coding of LSFS for packet loss

AU - Subasingha, Shaminda

AU - Murthi, Manohar

AU - Andersen, Søren Vang

PY - 2009/9/23

Y1 - 2009/9/23

N2 - Gaussian Mixture Model (GMM)-based Kalman predictive coders have been shown to perform better than baselineGMM Recursive Coders in predictive coding of Line Spectral Frequencies (LSFs) for both clean and packet loss conditions However, these stationary GMM Kalman predictive coders were not specifically designed for operation in packet loss conditions. In this paper, we demonstrate an approach to the the design of GMM-based predictive coding for packet loss channels. In particular, we show how a stationary GMM Kalman predictive coder can be modified to obtain a set of encoding and decoding modes, each with different Kalman gains. This approach leads to more robust performance of predictive coding of LSFs in packet loss conditions, as the coder mismatch between the encoder and decoder are minimized. Simulation results show that this Robust GMM Kalman predictive coder performs better than other baseline GMM predictive coders with no increase in complexity. To the best of our knowledge, no previous work has specifically examined the design of GMM predictive coders for packet loss conditions.

AB - Gaussian Mixture Model (GMM)-based Kalman predictive coders have been shown to perform better than baselineGMM Recursive Coders in predictive coding of Line Spectral Frequencies (LSFs) for both clean and packet loss conditions However, these stationary GMM Kalman predictive coders were not specifically designed for operation in packet loss conditions. In this paper, we demonstrate an approach to the the design of GMM-based predictive coding for packet loss channels. In particular, we show how a stationary GMM Kalman predictive coder can be modified to obtain a set of encoding and decoding modes, each with different Kalman gains. This approach leads to more robust performance of predictive coding of LSFs in packet loss conditions, as the coder mismatch between the encoder and decoder are minimized. Simulation results show that this Robust GMM Kalman predictive coder performs better than other baseline GMM predictive coders with no increase in complexity. To the best of our knowledge, no previous work has specifically examined the design of GMM predictive coders for packet loss conditions.

KW - GMM

KW - Kalman filtering

KW - Speech coding

KW - Vector quantization

UR - http://www.scopus.com/inward/record.url?scp=70349202234&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349202234&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2009.4960531

DO - 10.1109/ICASSP.2009.4960531

M3 - Conference contribution

SN - 9781424423545

SP - 4105

EP - 4108

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -