Iterative joint source-channel decoding of speech spectrum parameters over an additive white Gaussian noise channel

In this paper, we show how the Gaussian mixture modeling framework used to develop efficient source encoding schemes can be further exploited to model source statistics during channel decoding in an iterative framework to develop an effective joint source-channel decoding scheme. The joint probability density function (PDF) of successive source frames is modeled as a Gaussian mixture model (GMM). Based on previous work, the marginal source statistics provided by the GMM is used at the encoder to design a low-complexity memoryless source encoding scheme. The source encoding scheme has the specific advantage of providing good estimates to the probability of occurrence of a given source code-point based on the GMM. The proposed iterative decoding procedure works with any channel code whose decoder can implement the soft-output Viterbi algorithm that uses a priori information (APRI-SOVA) or the BCJR algorithm to provide extrinsic information on each source encoded bit. The source decoder uses the GMM model and the channel decoder output to provide a priori information back to the channel decoder. Decoding is done in an iterative manner by trading extrinsic information between the source and channel decoders. Experimental results showing improved decoding performance are provided in the application of speech spectrum parameter compression and communication.

[1]  David L. Neuhoff,et al.  Quantization , 2022, IEEE Trans. Inf. Theory.

[2]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[3]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[4]  Khalid Sayood,et al.  Use of residual redundancy in the design of joint source/channel coders , 1991, IEEE Trans. Commun..

[5]  Jan Skoglund,et al.  Vector quantization based on Gaussian mixture models , 2000, IEEE Trans. Speech Audio Process..

[6]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[7]  Peter Vary,et al.  Error concealment by near optimum MMSE-estimation of source codec parameters , 2000, 2000 IEEE Workshop on Speech Coding. Proceedings. Meeting the Challenges of the New Millennium (Cat. No.00EX421).

[8]  Joachim Hagenauer.  Source-controlled channel decoding , 1995, IEEE Trans. Commun..

[9]  Bhaskar D. Rao,et al.  Joint source-channel decoding of speech spectrum parameters over erasure channels using Gaussian mixture models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[10]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[11]  Peter Vary,et al.  Convergence behavior of iterative source-channel decoding , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[12]  Tim Fingscheidt,et al.  Combined source/channel (de-)coding: can a priori information be used twice? , 2000, 2000 IEEE International Conference on Communications. ICC 2000. Global Convergence Through Communications. Conference Record.

[13]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[14]  Stephan ten Brink,et al.  Convergence behavior of iteratively decoded parallel concatenated codes , 2001, IEEE Trans. Commun..

[15]  Russell M. Mersereau,et al.  Coding using Gaussian mixture and generalized Gaussian models , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[16]  Joachim Hagenauer,et al.  Iterative decoding of binary block and convolutional codes , 1996, IEEE Trans. Inf. Theory.

[17]  N. Gortz.  Iterative source-channel decoding using soft-in/soft-out decoders , 2000, 2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060).

[18]  Bhaskar D. Rao,et al.  Low-Complexity Source Coding Using Gaussian Mixture Models, Lattice Vector Quantization, and Recursive Coding with Application to Speech Spectrum Quantization , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[19]  Jack K. Wolf,et al.  On Tail Biting Convolutional Codes , 1986, IEEE Trans. Commun..

[20]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[21]  Peter Vary,et al.  On joint source-channel decoding for correlated sources , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[22]  A. Glavieux,et al.  Near Shannon limit error-correcting coding and decoding: Turbo-codes. 1 , 1993, Proceedings of ICC '93 - IEEE International Conference on Communications.

[23]  Bhaskar D. Rao,et al.  PDF optimized parametric vector quantization of speech line spectral frequencies , 2003, IEEE Trans. Speech Audio Process..

[24]  Jonas Samuelsson,et al.  Recursive coding of spectrum parameters , 2001, IEEE Trans. Speech Audio Process..

[25]  Peter Vary,et al.  Softbit speech decoding: a new approach to error concealment , 2001, IEEE Trans. Speech Audio Process..

[26]  Jörg Kliewer,et al.  Iterative source-channel decoding for robust image transmission , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[27]  N. Gortz.  On the iterative approximation of optimal joint source-channel decoding , 2001 .

[28]  Norbert Goertz.  On the iterative approximation of optimal joint source-channel decoding , 2001, IEEE J. Sel. Areas Commun..

[29]  Tim Fingscheidt,et al.  Joint source-channel (de-)coding for mobile communications , 2002, IEEE Trans. Commun..

[30]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[31]  Kuldip K. Paliwal,et al.  Speech Coding and Synthesis , 1995 .

[32]  Peter Vary,et al.  Iterative source-channel decoder using extrinsic information from softbit-source decoding , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).