D. Rainton
Time-Frequency Spectral Estimation of Speech - The Role of Variance In Estimator Performance
Abstract:In recent years there has been a growing interest amongst the speech research
community into the use of spectral estimators which circumvent the traditional
quasi-stationary assumption and provide greater time-frequency(t-f) resolution
than conventional spectral estimators, such as the short time Fourier power spectrum (STFPS). One distribution in particular, the Wigner distribution (WD),
has attracted considerable interest. However, experimental studies have indicated that, despite its improved t-f resolution, employing the WD as the front
end of a speech recognition system actually reduces recognition performance;
only by explicitly re-introducing t-f smoothing into the WD are recognition
rates improved. This paper, by making explicit the role of the variance of the
spectral estimator, provides a theoretical explanation for these previous experimental findings.