Nokia Research Center

Publications

• B. J. Borgstrom, A. Bernard, A. Alwan, “Error Recovery - Channel Coding and Packetization” Chapter 8 Automatic Speech Recognition on Mobile Devices and over Communication Networks, Springer-Verlag. pp. 163-185, 2008
• A. Bernard, Y. Gong and X. Cui, "Can back-ends be more robust than front-ends? Investigation over the Aurora-2 database", in Proceedings of ICASSP 2004, Montreal Canada, Volume 1, pp. 1025-8, May 2004
• L. Netsch and A. Bernard, "Automatic and language independent triphone training using phonetic tables”, in Proceedings of ICASSP 2004, Montreal, Canada, Volume 5, pp. 297-300, May 2004
• X. Cui, A. Bernard, and A. Alwan, "A Noise-Robust ASR Back-end Technique Based on Weighted Viterbi Recognition," in Proc. EUROSPEECH, Switzerland, pp. 2169-2172, Sept. 2003
• A. Bernard and A. Alwan, “Source and channel coding for low-bitrate distributed speech recognition systems”, IEEE Transactions on Speech and Audio Processing, Vol. 10, No. 8, pp 570—580, Nov. 2002
• A. Bernard, Ph.D. Dissertation: “Source & channel coding techniques for speech transmission and recognition”, Mar 2002
• A. Bernard, X. Liu, R. Wesel and A. Alwan, “Speech transmission using rate-compatible trellis codes (RCPT) and embedded source coding”, IEEE Transactions on Communications, Vol. 50, No. 2, pp. 309—320, Feb. 2002
• A. Bernardand A. Alwan, “Channel decoding - Viterbi speech recognition for wireless applications,” in Proc. EUROSPEECH, Aalborg, Denmark, vol. 4, pp. 2703-2706, Sept. 2001.
• A. Bernardand A. Alwan, “Source and channel coding for remote speech recognition over error-prone channel,” in Proc. of ICASSP, Salt-Lake City, UT, vol. 4, pp. 2613-2616, May 2001.
• A. McCree, T. Unno, A. Anandakumar, A. Bernard, and E. Paksoy, “An embedded adaptive multi-rate wideband speech coder”, in Proc. of ICASSP, Salt-Lake City, UT, vol. 4, pp. 2613-2616, May 2001
• A. Bernardand A. Alwan, “Perceptually based and embedded wideband CELP coding of speech”, in Proc. of Eurospeech, Budapest, Hungary, vol. 4, pp. 1543-1546, Sept. 1999
• A. Bernard, X. Liu, R. Wesel and A. Alwan “Embedded joint source-channel coding of speech using symbol puncturing in trellis code”, in Proc. of ICASSP, vol. 5, pp. 2427-30, Phoenix, March 1999
• A. Bernard, M.S. Thesis: “Source - channel coding of speech”, December 1998
• A. Bernard, X. Liu, R. Wesel and A. Alwan, “Channel adaptive joint source-channel coding of speech”, Proc. 32^nd Asilomar Conf. Signals, Systems, Computers, Pacific Grove, CA, vol. 1, pp. 357-61, Nov. 1998
• A. Bernard, J.J. Quisquater, B. Macq, M. Joye and N. Degand, “Practical solution to authentication of images with a secure camera”, in Proc. of SPIE Int. Soc. for Optical Eng., vol. 3022, pp. 290-7, 1997
• A. Bernard, Master Diploma Thesis: “Image authentication using a secure camera”, June 1996

Presentations

Lucent Bell Labs, IBM Research, U.C. San Diego, Stanford University, Boston University, Imperial College London, Conexant, Hughes Research Laboratory, Broadcom, Mindspeed, Sony, Altra Broadband Communications, UCLA Wireless symposium, Texas Instruments, Alcatel Telecom Research

Patents

• A. Bernard, “Algebraic codebook coding, system and method",US Patent 6847929 – Issued  Jan 25, 2005
• A. Bernardand L. Netsch, “Automatic language independent triphones training using a phonetic table”, US Patent 7289958 – Issued Oct 30, 207
• Y. Gong and A. Bernard, “Noise-resistant utterance detection”, U.S. Patent Application 10/649,270, Filed Aug. 27, 2003
• A. Bernardand Y. Gong, “Method to extend the operating range of joint additive and convolutive compensating algorithm using environment and statistics dependent channel estimation”, US Patent 7236930– Issued June 26, 2007
• A. Bernard and Y. Gong, “A middle-end solution to robust speech recognition: SNR dependent decoding and weighted Viterbi recognition”, U.S. Patent Application 10/823,059, Filed April 13, 2004