|
Vol: 56(70) No: 2 / June 2011 Improving the Sound Recording Quality of Wireless Sensors Using Automatic Gain Control Methods Gábor Gosztolya Department of Informatics, University of Szeged, Árpád tér 1., 6720 Szeged, Hungary, phone: (+36 62) 54-67-13, e-mail: ggabor@inf.u-szeged.hu, web: www.inf.u-szeged.hu/~ggabor László Tóth Research Group on Artificial Intelligence of the Hungarian Academy of Sciences, Tisza Lajos krt. 103., 6720 Szeged, Hungary, phone: (+36 62) 54-41-42, e-mail: tothl@inf-u-szeged.hu, web: www.inf.u-szeged.hu/~tothl Keywords: wireless sensors, sound quality, automatic gain control, volume level, speech recognition Abstract When performing speech recording it is desirable to have the speech signal in as a high quality as possible. In everyday recording conditions one of the most important aspects of sound quality is to have a uniform volume level, because it is very hard to understand (and to automatically recognize) an utterance with a volume level that varies considerably. Of course this uniform volume level should also be an average one, avoiding either too loud or too quiet recordings. To overcome this problem usually an approach called Automatic Gain Control is used, which is an adaptive method for controlling microphone sensitivity (gain). Wireless sensors are recent, low-powered devices, which are ideal for recording and transmitting observations such as speech, thus they are a good area for applying automatic gain control. Due to their low power consumption, however, only very simple solutions can be implemented. Here we will present a general gain control algorithm, then introduce two variations that we test in a situation which simulates the actual use. We perform evaluations by using two types of measurement: the first one compares local volume levels to recordings made under ideal conditions, while in the second we measure the understandability of the recordings made by applying standard speech recognition techniques. Our results in both cases confirm that it is indeed an area where automatic gain control can be applied, and that both our algorithms perform well in practice. References [1] S. Ramanathan and M. Steenstrup, “A survey of routing techniques for mobile communications networks”, Mobile Networks and Applications, vol. 1, no. 2, pp. 89 – 104, 1996. [2] S. Kang, H. Choi, H. Yoon and K. Park, “Automatic gain control for the uniform amplitude of interferent signal in a Laser Doppler Vibrometer”, Proceedings of SICE-ICASE International Joint Conference SICE-ICCAS 2006, Busan, South Korea, pp. 1085 – 1090, 2006. [3] C. S. Bae, “An automatic pacemaker sensing algorithm using automatic gain control”, Proceedings of the 1999 IEEE Region 10 Conference TENCON 99, Cheju Island, South Korea, pp. 375 – 378, 1999. [4] Z. Tüske, P. Mihajlik, Z. Tobler and T. Fegyó, “Robust Voice Activity Detection based on the entropy of noise-suppressed spectrum”, 9th European Conference on Speech Communication and Technology Interspeech 2005 - Eurospeech, Lisboa, Portugal, pp. 245 – 248, 2005. [5] J.M. Górriz, J. Ramírez, J.C. Segura and S. Hornillo, “Voice Activity Detection using higher order statistics”, Proceedings of the 8th International Work-Conference on Artificial Neural Networks IWANN 2005, Barcelona, Spain, pp. 837 – 844, 2005. [6] L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals, Prentice-Hall, New Jersey, 1978. [7] J. Benesty, M. M. Sondhi and Y. Huang, Springer Handbook of Speech Processing, Springer-Verlag, Berlin, 2008. [8] L. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition, Prentice-Hall, New Jersey, 1993. [9] A. Kocsor, L. Tóth, A. Kuba Jr., K. Kovács, M. Jelasity, T. Gyimóthy and J. Csirik, “A comparative study of several feature space transformation and learning methods for phoneme classification”, International Journal of Speech Technology, vol. 3, no. 3/4, pp. 263 – 276, 2000. [10] R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, Wiley & Sons, New York, 1973. [11] C. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995. [12] X. Huang, A. Acero and H.-W. Hon, Spoken Language Processing, Prentice Hall, New Jersey, 2001. [13] S. Young, “The HMM Toolkit (HTK) (software and manual)”, http://htk.eng.cam.ac.uk/, 1995. [14] F. J. Damerau, Markov Models and Linguistic Theory: An Experimental Study of a Model for English, Mouton De Gruyter, Berlin, 1971. [15] F. Jelinek, Statistical Methods for Speech Recognition, The MIT Press, Cambridge, USA, 1997. [16] G. Gosztolya, D. Paczolay and L. Tóth, “Automatic Gain Control algorithms for wireless sensors”, Proceedings of the International Joint Conference on Computational Cybernetics and Technical Informatics ICCC-CONTI 2010, Timisoara, Romania, pp. 401 – 406, 2010. [17] H. G. Hirsch and C. Ehrlicher, “Noise estimation techniques for robust speech recognition”, Proceedings of the International Conference on Acoustic, Speech, and Signal Processing ICASSP 1995, Detroit, USA, pp. 153 – 156, 1995. [18] M. Holmberg and D. Gelbart, “Automatic Speech Recognition with an adaptation model motivated by auditory processing”, IEEE Transactions on Audio, Speech and Language Processing, vol. 14, no. 1, pp. 43 – 49, 2005. |