Paper Details

In general voice communication, speech is always affected by background noise whichreduces perception quality of the speech signal. The incoming speech from far end speaker and nearend noise reaches our ear at the same time, noise cannot be cancelled. Hence speech signal isenhanced with respect to variation in the near end noise. In this work, we propose two speechenhancing methods in order to combat near end noise. In first method, suitable gain is derived andsmoothened for speech enhancement using weighted hearing curve and overall speech is enhanced togive better quality and perception. In second method we determine dominant frequenciescomponents of speech signal and enhance only those frequencies instead enhancing the entire signal.The energy needed for enhancing is reduced in later approach when compared to former one. So amethod of energy conservation is achieved. Quality of enhanced speech signals is measured usingperception evaluation of speech quality (PESQ) which is an ITU recommended standard for speechquality assessment.

Premananda B.S., Manoj, Uma B.V., “Near-End Perception Enhancement using Dominant Frequency”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 1, Issue 6, pp. 411-417, June 2014.