Skip to main content

Table 3 Influence of the number of differential coefficients with the HLDA transformation on phone recognition rates on the Test part of the original FPSD database (without vector conversion)

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

36 monophone HMMs with 16 Gaussians per state \(+\) Bigram Accuracy (%) Correct (%)
Exp 1 : \(39 \ MFCC\) coefficients 61.89 67.62
Exp 2 : \(52 \ MFCC\) coefficients 58.49 65.29
Exp 3 : \(HLDA \ (52\rightarrow 39)\) 63.59 69.43