The analysis and design of architecture systems for speech recognition on modern handheld-computing devices

ABSTRACT

Growing demand for high performance in embedded systems is creating new opportunities to use speech recognition systems traditionally executed only on high performance systems. In several ways, the needs of embedded computing differ from those of more traditional general-purpose systems. Embedded systems have more stringent constraints on cost and power consumption that lead to design bottlenecks for many computationally-intensive applications. This paper characterizes the speech recognition process on hand-held mobile devices and evaluates the use of modern architecture features and compiler techniques for performing real-time speech recognition. We evaluate the University of Colorado Sonic speech recognition software on the IMPACT architectural simulator and compiler framework. Experimental results show that by using a strategic set of compiler optimization, a 500MHz processor with moderate levels of instruction-level parallelism and cache resources can meet the real-time computing and power constraints of an advanced speech recognition application.

REFERENCES

• 1: Khaldoun Shobaki, John-Paul Hosom, and Ronald Cole. The OGI Kids' Speech Corpus and Recognizers. In Proceedings of the International Conference on Spoken Language Processing (ICSLP), Beijing, China, October 2000.
• 2: K. Agaram, S. Keckler, and D. Burger. A Characterization of Speech Recognition on Modern Computer Systems. In 4th IEEE Workshop on Workload Characterization, December 2001.
• 3: Kai-Fu Lee, Hsiao-Wuen Hon, and Raj Reddy. An Overview of the SPHINX Speech Recognition System. IEEE Transactions on Acoustics, Speech and Signal Processing, 38:35--44, 1990.
• 4: S. Vlaovic, R. Uhlig. Performance of Natural I/O Applications. 2nd Workshop on Workload Characterization. October 1999.
• 5: http://www.crhc.uiuc.edu/Impact (link checked on 04/14/03)
• 6: Pellom, B., Hacioglu, K., Recent Improvements in the Sonic ASR System for Noisy Speech: the SPINE task. Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hong Kong, April 2003.
• 7: Pellom, B., Sonic: The University of Colorado Continuous Speech Recognition System. Technical Report TR-CSLR-2001-01, University of Colorado, March 2001.
• 8: M. Ravishankar, Efficient Algorithms for Speech Recognition. PhD Thesis, Carnegie Mellon University, 1996.
• 9: S.J. Young, N.H. Russell, J.H.S. Thornton, Token Passing: A Simple Conceptual Model for Connected Speech Recognition Systems. Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR.38, 1989.
• 10: Bryan Pellom, Ruhi Sarikaya, John Hansen, Fast Likelihood Computation in Nearest-Neighbor Based Search for Continuous Speech Recognition. In IEEE Signal Processing Letters, vol. 8, no. 8, pp. 221-224, August 2001.
• 11: Nigel Paver. Intel XScale Micro-Architecture with Wireless MMX technology. www.intel.com/pca/developernetwork, Volume 4, Summer 2002.
• 12: The Intel PXA250 Applications Processor. White Paper, Intel, February 2002.
• 13: PXA250 and PXA210 Application Processors Developer's Manual, Intel, 2002.
• 14: David Brooks , Vivek Tiwari , Margaret Martonosi, Wattch: a framework for architectural-level power analysis and optimizations, Proceedings of the 27th annual international symposium on Computer architecture, p.83-94, June 2000, Vancouver, British Columbia, Canada
• 15: Hwu et al. The Superblock: An Effective Structure for VLIW and Superscalar Compilation. Center for Reliable and High-Performance Computing. University of Illinois, Urbana, IL. February, 1992.
• 16: A. P. Chandrakasan, S. Sheng, and R. W. Brodersen. Low-power CMOS digital design. IEEE Journal of Solid-State Circuits, vol. 27, no. 4, pp. 473-484, April 1992

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.3 SPECIAL-PURPOSE AND APPLICATION-BASED SYSTEMS
      Subjects: Real-time and embedded systems

General Terms:
Design, Measurement, Performance

Keywords:
embedded systems, performance, speech recognition