Error Recovery: Channel Coding and Packetization
Distributed Speech Recognition (DSR) systems rely on efficient transmission of speech information from distributed clients to a centralized server. Wireless or network communication channels within DSR systems are typically noisy and bursty. Thus, DSR systems must utilize efficient Error Recovery (ER) schemes during transmission of speech information. Some ER strategies, referred to as forward error control (FEC), aim to create redundancy in the source coded bitstream to overcome the effect of channel errors, while others are designed to create spread or delay in the feature stream in order to overcome the effect of bursty channel errors. Furthermore, ER strategies may be designed as a combination of the previously described techniques. This chapter presents an array of error recovery techniques for remote speech recognition applications.
This chapter is organized as follows. First, channel characterization and modeling are discussed. Next, media-specific FEC is presented for packet erasure applications, followed by a discussion on media-independent FEC techniques for bit error applications, including general linear block codes, cyclic codes, and convolutional codes. The application of unequal error protection (UEP) strategies utilizing combinations of the aforementioned FEC methods is also presented. Finally, frame-based interleaving is discussed as an alternative to overcoming the effect of bursty channel erasures. The chapter concludes with examples of modern standards for channel coding strategies for distributed speech recognition (DSR).
KeywordsChannel Code Cyclic Code Convolutional Code Error Recovery Unequal Error Protection
Unable to display preview. Download preview PDF.
- Bernard, A., and Alwan, A. (2001). Joint Channel Decoding- Viterbi Recognition for Wireless Applications. Proceedings of Europspeech, vol. 3, pp. 2703-2706.Google Scholar
- Bernard, A. (2002). Source and Channel Coding for Speech Transmission and Remote Speech Recognition, PhD Thesis, University of California, Los Angeles.Google Scholar
- Blahut, R.E. (2004). Algebraic Codes for Data Transmission. Cambridge University Press, Cambridge, UK.Google Scholar
- Bolot, J.-C. (2003). End-to-End Packet Delay and Loss Behavior in the Internet. ACM Sig-comm, pp. 289-298.Google Scholar
- Elliot, E. (1963). Estimates of Error Rates for Codes on Bursty Noise Channels. Bell Systems Technical Journal, vol. 42, no. 9.Google Scholar
- ETSI EN 300 909 v7.3.1 (1998). Digital Cellular Telecommunications System(Phase 2+)(GSM); Channel Coding.Google Scholar
- ETSI ES 201 108 v1.1.2 (2000). Distributed Speech Recognition; Front-end Feature Extrac-tion Algorithm; Compression Algorithms.Google Scholar
- Han, K.J., Srinivasamurthy, N., and Narayanan, S. (2004). Robust Speech Recognition over Packet Networks: An Overview. Proceedings of ICSLP, vol. 3, pp. 1791-1794.Google Scholar
- Hirsch, H.G., and Pearce, D. (2000). The AURORA Experimental Framework for the Per-formance Evaluation of Speech Recognition Systems under Noisy Condition. In Proceed-ings of ISCA ITRW ASR 2000.Google Scholar
- James, A.B., and Milner, B.P. (2004). An Analysis of Interleavers for Robust Speech Recogni-tion in Burst-Like Packet Loss. In Proceedings of ICASSP, vol. 1, pp. 853-856.Google Scholar
- Jiao, C., Schwiebert, L., and Xu, B. (2002). On Modeling the Packet Error Statistics in Bursty Channels. IEEE LCN, pp. 534-538.Google Scholar
- Leon-Garcia, A. (2007). Probability and Random Processes for Electrical Engineers. Prentice-Hall.Google Scholar
- Peinado, A.M., Gomez, A.M., Sanchez, V., Perez-Cordoba, J.L., and Rubio, A.J. (2005a). Packet Loss Concealment Based on VQ Replicas and MMSE Estimation Applied to Dis-tributed Speech Recognition. Proceedings of ICASSP. vol. 1, pp. 329-330.Google Scholar
- Sklar, B. (1997). Rayleigh Fading Channels in Mobile Digital Communication Systems Part 1: Characterization. IEEE Communications Magazine, pp. 90-100.Google Scholar
- Wesel, R.D. (2003). Convolutional Codes, from Encyclopedia of Telecommunications. Wiley, New York.Google Scholar
- Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., and Woodland, P. (2000). The HTK Book. Microsoft Corporation.Google Scholar