EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Phone accuracies (percent) of vowels, semivowels, stops, fricatives, nasals, and silence

From: Integrated exemplar-based template matching and statistical modeling for continuous speech recognition

	Vowels	Semivowels	Stops	Fricatives	Nasals	Silence
HMM baseline	63.48	72.47	73.65	74.83	72.03	86.02
KL distance	68.30	76.52	73.45	72.37	72.53	85.48
LLR distance	68.32	76.85	75.65	71.95	72.66	85.57

Back to article page