Skip to main content

Table 11 Best-fitted multivariate distribution based on the energy test for DCT coefficients of five phoneme classes in different frame lengths

From: Speech signal modeling using multivariate distributions

Phoneme class Frame length
20 ms 30 ms 100 ms 500 ms
Semivowel/glide MLD MGLD, p = 0.75 MLD MGLD, p = 0.75 MGLD, p = 0.75 MLD MGLD, p = 0.75 MLD
0.00 0.01 0.00 0.01 0.00 0.00 0.00 0.00
Vowel MLD MGLD, p = 0.75 MLD MGLD, p = 0.75 MGLD, p = 0.75 MLD MGLD, p = 0.75 MLD
0.00 0.01 0.00 0.01 0.01 0.01 0.01 0.01
Nasal MGLD, p = 0.75 MGLD, p = 0.50 MGLD, p = 0.75 MLD MGLD, p = 0.75 MGLD, p = 0.50 MGD MGLD, p = 0.50
0.00 0.01 0.00 0.01 0.00 0.01 0.00 0.02
Fricative MGLD, p = 0.75 MLD MGLD, p = 0.75 MLD MGLD, p = 0.50 MGLD, p = 0.75 MGLD, p = 0.75 MGLD, p = 0.50
0.01 0.01 0.00 0.01 0.00 0.01 0.00 0.00
Stop MLD CLD MLD CLD MLD MGLD, p = 0.75 MGLD, p = 0.75 MGLD, p = 0.50
0.05 0.10 0.04 0.08 0.01 0.01 0.00 0.00