Skip to main content

Table 4 Influence of the number of differential coefficients with the HLDA transformation on phone recognition rates on the core test of the TIMIT database

From: A preliminary study on improving the recognition of esophageal speech using a hybrid system based on statistical voice conversion

39 monophone HMMs with 16 Gaussians per state \(+\) Bigram Accuracy (%) Correct (%)
Exp 1 : \(39 \ MFCC\) coefficients 69.19 71.78
Exp 2 : \(52 \ MFCC\) coefficients 67.96 71.38
Exp 3 : \(HLDA \ (52\rightarrow 39)\) 71.32 74.07