The major goal of this research is to reduce the discrepancy in recognition performance between normal and abnormal speech, given that reference templates were derived only from normal speech. A method is devised that uses the differences in spectral slope between linear predictive coding log magnitude spectra to weight the point-by-point energy differences between the spectra. The distances of all reference tokens of like phonemes are combined to form a smallest cumulative distance (SCD) method. When SCD is combined with the method of slope-dependent weighting (SDW), the most significant success is obtained. In terms of error rates for a fixed phoneme vector length of five, SDW+SCD is found to reduce the difference in error rate between normal and abnormal speech by approximately 50%.
Robust recognition of loud and Lombard speech in the fighter cockpit environment
Robuste Erkennung von lauter Sprache und Lombardsprache im Cockpit eines Kampfflugzeuges
1989
4 Seiten, 8 Quellen
Aufsatz (Konferenz)
Englisch
Adaptive noise cancellation in a fighter cockpit environment
Tema Archiv | 1984
|Advanced Integrated Fighter Cockpit Study
NTIS | 1971
|Rules for fighter cockpit automation
Tema Archiv | 1988
|British Library Conference Proceedings | 1993
|F-15 Dual Role Fighter Cockpit Integration
SAE Technical Papers | 1983
|