Using a new Discretization of the Fourier Transform to Discriminate Voiced From Unvoiced Speech

Abstract

In Automatic Speech Recognition, Voice Synthesis, Speaker Identification and identifying laringeal diseases, it is critical to classify speech segments as voiced or unvoiced. Several techniques have been proposed for this issue during the last twenty years, unfortunately, they either have especial cases where the result is unreliable or need to use not only the present segment of speech but the next one as well, this fact limits its applications (i.e Continuos Speech recognition). In this paper we present an alternative to voiced/unvoiced classification using a Discretization of the Continuos Fourier Transform.

Coincident frequencies and relative phases among brain activity and hormonal signals

“…Some of the numerical examples given in [ 20 , 26 ] deal with singular or oscillatory signals for which our discrete Fourier transform performs well, whereas the usual discrete Fourier transform, i.e., the so-called Fast Fourier Transform, fails to yield the correct spectrum. Our discrete Fourier transform can also be used in the frequency analysis of transient signals, like those appearing in some voice recognition problems [ 27 ].…”