Table 1 Evolution of DER and acoustic-model size according to the number of Gaussian components per state (context-free models). The acoustic vectors are composed of 39 coefficients (12 PLP plus energy with 
and 
). 
isolated-digit recognition tests were performed on the corpus BDSON (digit/clean).
and 
). 
isolated-digit recognition tests were performed on the corpus BDSON (digit/clean).From: Compact Acoustic Models for Embedded Speech Recognition
No. of gauss/state | No. of parameters | DER |
|---|---|---|
2 | 17 064 | 1,48% |
4 | 34 128 | 0,96% |
128 | 1 092 096 | 0,96% |