WinSnoori processes speech files accompanied
by their phonetic and orthographic annotations respectively giving the description
of the speech signal in terms of phonemes and words.
WinSnoori:
- displays the sound signal or a portion of the
signal covering a maximum duration of 8 seconds for large speech files.
- displays the phonetic and orthographic annotations
of the signal.
- displays one of the six different signal
spectrograms.
- detects spectral peaks (obtained either by cepstral
smoothing or by LPC).
- displays the fundamental frequency (the pitch or voicing frequency)
and allows the F0 contour as well as the speech rate to be modified.
- allows the editing of speech and annotation files.
- allows the display of spectral slices (for eight different spectra at
same time).
- allows manual editing of parameters for the Klatt
synthesizer and provides tools to automatic copy synthesis (automatic formant
tracking, adjustment of formant amplitudes).