TY - JOUR
T1 - Gaussian mixture kalman predictive coding of line spectral frequencies
AU - Subasingha, Shaminda
AU - Murthi, Manohar N.
AU - Andersen, Søren Vang
N1 - Funding Information:
Manuscript received March 28, 2008; revised July 17, 2008. Current version published February 11, 2009. This work was supported in part by the U.S. National Science Foundation via Awards CCF-0347229 and CNS-0519933. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Tim Fingscheidt.
PY - 2009/2
Y1 - 2009/2
N2 - Gaussian mixture model (GMM)-based predictive coding of line spectral frequencies (LSFs) has gained wide acceptance. In such coders, each mixture of a GMM can be interpreted as defining a linear predictive transform coder. In this paper, we use Kalman filtering principles to model each of these linear predictive transform coders to present GMM Kalman predictive coding. In particular, we show how suitable modeling of quantization noise leads to an adaptive a posteriori GMM that defines a signal-adaptive predictive coder that provides improved coding of LSFs in comparison with the baseline recursive GMM predictive coder. Moreover, we show how running the GMM Kalman predictive coders to convergence can be used to design a stationary GMM Kalman predictive coding system which again provides improved coding of LSFs but now with only a modest increase in run-time complexity over the baseline. In packet loss conditions, this stationary GMM Kalman predictive coder provides much better performance than the recursiveGMMpredictive coder, and in fact has comparable mean performance to a memoryless GMM coder. Finally, we illustrate how one can utilize Kalman filtering principles to design a postfilter which enhances decoded vectors from a recursiveGMMpredictive coder without any modifications to the encoding process.
AB - Gaussian mixture model (GMM)-based predictive coding of line spectral frequencies (LSFs) has gained wide acceptance. In such coders, each mixture of a GMM can be interpreted as defining a linear predictive transform coder. In this paper, we use Kalman filtering principles to model each of these linear predictive transform coders to present GMM Kalman predictive coding. In particular, we show how suitable modeling of quantization noise leads to an adaptive a posteriori GMM that defines a signal-adaptive predictive coder that provides improved coding of LSFs in comparison with the baseline recursive GMM predictive coder. Moreover, we show how running the GMM Kalman predictive coders to convergence can be used to design a stationary GMM Kalman predictive coding system which again provides improved coding of LSFs but now with only a modest increase in run-time complexity over the baseline. In packet loss conditions, this stationary GMM Kalman predictive coder provides much better performance than the recursiveGMMpredictive coder, and in fact has comparable mean performance to a memoryless GMM coder. Finally, we illustrate how one can utilize Kalman filtering principles to design a postfilter which enhances decoded vectors from a recursiveGMMpredictive coder without any modifications to the encoding process.
KW - Gaussian mixture models (GMMs)
KW - Kalman filtering
KW - Speech coding
KW - Vector quantization (VQ)
UR - http://www.scopus.com/inward/record.url?scp=70350451583&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70350451583&partnerID=8YFLogxK
U2 - 10.1109/TASL.2008.2008735
DO - 10.1109/TASL.2008.2008735
M3 - Article
AN - SCOPUS:70350451583
VL - 17
SP - 379
EP - 391
JO - IEEE Transactions on Speech and Audio Processing
JF - IEEE Transactions on Speech and Audio Processing
SN - 1558-7916
IS - 2
ER -