Restoration of Authentic Features in Tracheoesophageal Speech by a Multi-Resolution Approach

O. Schleusing, R. Vetter, Ph. Renevey, J. Krauss, F.N. Reale, V. Schweizer, and J.-M. Vesin (Switzerland)


Speech Processing, Speech restoration, Frequency estimation, Adaptive signal processing, Matched filters, Wavelet transforms


This paper presents a novel method for the restoration of authentic features in pathological speech uttered by subjects with laryngeal disorders. The pathological excitation is replaced by concatenation of randomly chosen healthy reference patterns. To restore authentic features intervals between subsequent glottal waves are obtained through a multi-resolution approach. Short-term pitch variability is reproduced through a statistical variation model. Middle-term pitch variability exploits the correlation at the middle-term time scale between pitch and signal envelope. Long-term variability is obtained through adaptive wavetable oscillators; a novel, reliable and computationally efficient method. Performance was assessed with respect to three authentic features, namely breathiness, prosody and naturalness. Preliminary results have shown that breathiness of the restored voice is clearly reduced while prosody related features are slightly improved.

Important Links:

Go Back