Speech Coding Based on Compressed Sensing and Sparse Representation

Abstract:

In this paper, we propose a novel speech coding scheme based on compressed sensing and sparse representation. Compressed sensing (CS) attracts great interest for its ability to utilize a few measurements to recover original signals. Measurements preserve part of speech features while projected by row echelon matrix. A dictionary is learned in order to contain redundant information about speech measurements. The synthesized speech is recovered from a sparse approximation of the corresponding measurement. A rear low-pass filter is adopted to improve the subject quality of synthesized speech. Results show that the proposed coding scheme has achieved average Mean Opinion Score (MOS) of the synthesized speech 3.083 in an appropriate bit rate (4.2 Kbps), which outperforms the quality of Code excited linear prediction (CELP).

• Periodical: Applied Mechanics and Materials (Volume 667)
• Pages: 242-247
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.667.242
• Online since: October 2014
• Authors: Shang Jing Li*, Qi Zhu
• Keywords: Compressed Sensing, Measurement Modeling, Sparse Representation, Speech Coding

References

[1] Donoho D L. Compressed sensing. IEEE Transaction on Information Theory, 2006, vol. 52, no. (4) , pp.1289-1306.

[2] Ye L, Yang Z, Wang T J, et al. Compressed Sensing of Speech Signal Based on Row Echelon Measurement Matrix and Dual Affine Scaling Interior Point Reconstruction Method. Acta Electronica Sinca, 2012, vol. 40, no. 3, pp.429-434.

[3] Elad M. Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing (Springer, USA 2010).

DOI: 10.1007/978-1-4419-7011-4

[4] Tropp J A, Gilbert A C. Signal Recovery Form Random Measurements Via Orthogonal Matching Pursuit. IEEE Transactions on Information Theory, 2007, vol. 53, pp.4655-4666.

DOI: 10.1109/tit.2007.909108

[5] Engan K, Aase S, Hakon-Husoy J. Method of optimal directions for frame design. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1999. Proceedings. 1999, vol. 5, pp.2443-2446.

DOI: 10.1109/icassp.1999.760624

[6] Aharon M, Elad M, Bruckstein A. K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Re presentation. IEEE Transactions on Signal Processing, 2006, vol. 54, no. 11, pp.4311-4322.

DOI: 10.1109/tsp.2006.881199

[7] Skretting K, Engan K. Recursive Least Squares Dictionary Learning Algorithm. IEEE Transactions on Signal Processing, 2010, vol. 58, no. 4, pp.2121-2130.

DOI: 10.1109/tsp.2010.2040671

[8] Ye L, Yang Z, Sun L H. New low bit rate speech coding scheme based on compressed sensing. Chinese Journal of Scientific Instrument, 2011, vol. 32, no. 12, pp.2688-2692.

[9] National Communication System, Office of Technology and Standards. Federal Standard 1016, Analog to digital conversion of radio voice by 4800 bit/second code excited linear predictive coding, (1991).