Clean speech reconstruction from noisy mel-frequency cepstral coefficients using a sinusoidal model

This paper extends the technique of speech reconstruction from MFCCs by considering the effect of noisy speech. To reconstruct a clean speech signal from noise contaminated MFCCs an estimate of the clean mel-filterbank vector is required together with a robust estimate of the pitch. This work applies spectral subtraction to the mel-filterbank vector (derived from noisy MFCCs) to provide a clean speech spectral estimate. To obtain a reliable estimate of pitch a robust extraction technique is used. Spectrograms and informal listening tests reveal that a clean speech signal can be successfully reconstructed from the noisy MFCCs. Pitch errors are shown to manifest themselves as artificial sounding bursts in the reconstructed speech signal. Incorrect estimates of the spectral envelope introduce periods of noise into the reconstructed speech.