On timing in time-frequency analysis of speech signals

Abstract

The objective of this paper is to demonstrate the importance of position of the analysis time window in time-frequency analysis of speech signals. Speech signals contain information about the time varying characteristics of the excitation source and the vocal tract system. Resolution in both the temporal and spectral domains is essential for extracting the source and system characteristics from speech signals. It is not only the resolution, as determined by the analysis window in the time domain, but also the position of the window with respect to the production characteristics that is important for accurate analysis of speech signals. In this context, we propose an event-based approach for speech signals. We define the occurrence of events at the instants corresponding to significant excitation of the vocal tract system. Knowledge of these instants enable us to place the analysis window suitably for extracting the characteristics of the excitation source and the vocal tract system even from short segments of data. We present a method of extracting the instants of significant excitation from speech signals. We show that with the knowledge of these instants it is possible to perform prosodic manipulation of speech and also an accurate analysis of speech for extracting the source and system characteristics.