Griffith University

B Engineering (Hons), PhD

Senior Lecturer, Griffith School of Engineering

Contact details for Dr Stephen So

Research expertise

Dr So has active research interests in digital signal processing, specifically in the areas of speech processing (low bitrate speech coding, speech enhancement using Wiener and Kalman filtering and distributed speech recognition), image coding, as well as efficient block and vector quantisation schemes. He is currently a full research member of the Institute for Integrated and Intelligent Systems and the Signal Processing Laboratory.

Current teaching areas

• Signals and Systems
• Digital Signal Processing
• Advanced Digital Signal Processing

Publications

• S. So and K.K. Paliwal, "Modulation-domain Kalman filtering for single-channel speech enhancement'', Speech Commun., vol. 53, no. 6, pp. 818-829, July 2011. 
• S. So and K.K. Paliwal, "Suppressing the influence of additive noise on Kalman gain for low residual noise speech enhancement'', Speech Commun., vol. 53, no. 3, pp. 355-378, Mar. 2011.
  
• K.K. Paliwal, J.G. Lyons, S. So, A.P. Stark, K.K. Wojcicki, "Comparative evaluation of speech enhancement methods for robust automatic speech recognition", in Proc. 4th Int. Conf. Signal Processing and Communication Systems (ICSPCS 2010), Gold Coast, Australia, Dec. 2010.
• S. So and K.K. Paliwal, "Single-channel speech enhancement using Kalman filtering in the modulation domain", in Proc. Interspeech 2010, Makuhari, Chiba, Japan, Sept. 2010.
• S. So and K.K. Paliwal, "Fast converging iterative Kalman filtering for speech enhancement using long and overlapped windows with large side lobe attenuation", in Proc. Interspeech 2010, Makuhari, Chiba, Japan, Sept. 2010.
• S. So, K.K. Wojcicki, J.G. Lyons, A.P. Stark and K.K. Paliwal, "Kalman filter with phase spectrum compensation algorithm for speech enhancement", in Proc. Institute of Electrical and Electronics Engineers Int. Conf Acoust,. Speech, Signal Processing, Taipei, Taiwan ROC, April 2009.
• S. So and K.K. Pailwal, "Quantization of speech features: source coding", in Automatic Speech Recognition on Mobile Devices and over Communication Networks, Z.H. Tan and B. Lindberg, Eds., London: Springer-Verlag, 2008, pp. 131-161. (ISBN: 978-1-84800-142-8)
• S. So and K.K. Paliwal, "A long state vector Kalman filter for speech enhancement", in Proc. Int. Conference Spoken Language Processing (INTERSPEECH 2008), Brisbane, Australia, September 2008.
• K.K. Wojcicki, S. So and K.K. Paliwal, "The effect of the additivity assumption on time and frequency domain Wiener filtering for speech enhancement", in Proc. European Conference on Speech Communication Technology (EUROSPEECH 2007) , Antwerp, Belgium, Aug 2007.
• S. So and K.K. Paliwal, "A comparative study of LPC parameter representations and quantisation schemes for wideband speech coding", Digital Signal Processing, vol. 17, no. 1, pages 114-137, Jan. 2007.
• S. So and K.K. Paliwal, "Efficient product code vector quantisation using the switched split vector quantiser", Digital Signal Processing, vol. 17, no. 1, pages 138-171, Jan. 2007.
• S. So and K.K. Paliwal, "Empirical lower bound on the bitrate for the transparent memoryless coding of wideband LPC parameters", Institute of Electrical and Electronics Engineers Signal Proc. Lett., volume 13, no. 9, Sept. 2006.
• S. So and K.K. Paliwal, "Scalable distributed speech recognition using Gaussian mixture model-based block quantisation", Speech Commun., vol. 48, pages 746-758, 2006.
• S. So and K.K. Paliwal, "Multi-frame GMM-based block quantisation of line spectral frequencies", Speech Commun., volume 47, pages 265-276, Nov. 2005.
• K.K. Paliwal and S. So, "Low complexity GMM-based block quantisation of images using the discrete cosine transform", Signal Processing: Image Communication, volume 20, pages 435-446, June 2005.
• K.K. Paliwal and S. So, "A fractional bit encoding technique for GMM-based block quantisation of images", Digital Signal Processing, volume 15, pages 255-275, May 2005.
• S. So and K.K. Paliwal, "Multi-frame GMM-based block quantisation for distributed speech recognition under noisy conditions", in Proc. Institute of Electrical and Electronics Engineers Int. Conf. Acoust., Speech, Signal Processing Toulouse, France, May 2006, pages I-189--192.
• S. So and K.K. Paliwal, "Improved noise-robustness in distributed speech recognition via perceptually-weighted vector quantisation of filterbank energies", in Proc. European Conference on Speech Communication and Technology (EUROSPEECH 2005), Lisbon, Portugal, Sept. 2005.
• S. So and K.K. Paliwal, "Switched split vector quantisation of line spectral frequencies for wideband speech coding", in Proc. European Conference on Speech Communication and Technology (EUROSPEECH 2005), Lisbon, Portugal, Sept. 2005.
• S. So and K.K. Paliwal, "A comparison of LSF and ISP representations for wideband LPC parameter coding using the switched split vector quantiser", in Proc. Institute of Electrical and Electronics Engineers Int.. Symp. on Signal Processing and Its Applications, Sydney, Australia, Aug. 2005.
• S. So and K.K. Paliwal, "Multi-frame GMM-based block quantisation of line spectral frequencies for wideband speech coding", in Proc. Institute of Electrical and Electronics Engineers Int. Conf. Acoust., Speech, Signal Processing, Philadelphia, Mar. 2005, volume I, pages 121-124.
• S. So and K.K. Paliwal, "Efficient vector quantisation of line spectral frequencies using the switched split vector quantiser", in Proc. Int. Conf. Spoken Language Processing (ICSLP 2004), Jeju, South Korea, Oct. 2004.
• K.K. Paliwal and S. So, "Scalable distributed speech recognition using multi-frame GMM-based block quantization", in Proc. Int. Conf. Spoken Language Processing (ICSLP 2004), Jeju, South Korea, Oct. 2004.
  K.K. Paliwal and S. So, "Multiple frame block quantisation of line spectral frequencies using Gaussian mixture models", in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing (ICASSP 2004), Montreal, May 2004, vol. I, pp. 149-152.
• S. So and K.K. Paliwal, "Efficient block coding of images using Gaussian mixture models", in Proc. Fourth Australasian Workshop on Signal Processing and Applications (WoSPA-2002), Brisbane, Australia, Dec. 2002, pp. 71-74.