Speech active level estimation in noisy conditions

We present a new method for speech active level estimation which combines a novel algorithm based on voiced speech energy extraction with the standardized ITU-T Recommendation P.56. At poor signal-to-noise ratios, the algorithm estimates the active level by identifying intervals of voiced speech and summing the energy of the pitch harmonics in the time-frequency domain while rejecting that of the noise. We compare the performance of our method with that of ITU-T P.56 on the TIMIT database and demonstrate that it performs exceptionally well in both high and low levels of additive noise.