4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Speech Recognition Using a Strong Correlation Assumption for the Instantaneous Spectra

J. Ming, P. O'Boyle, J. McMahon, F. J. Smith

School of Electrical Engineering and Computer Science, The Queen's University of Belfast, Belfast, UK

The conventional independence assumption made for the evolving speech spectra is replaced by a strong correlation assumption, which then leads to a new stochastic model. This model implements a nonlinear interpolation between the lower and upper bounds of the joint probability distributions. The advantage of the new model over other correlation-based modelling approaches is that it has a low parameter complexity, the same as that in models based on the independence assumption. Experiments on a speaker-independent E-set database show the effectiveness of this new modelling approach.

Full Paper

Bibliographic reference.  Ming, J. / O'Boyle, P. / McMahon, J. / Smith, F. J. (1996): "Speech recognition using a strong correlation assumption for the instantaneous spectra", In ICSLP-1996, 1061-1064.