Skip to main content
Search all SpringerOpen articles
EURASIP Journal on Audio, Speech, and Music Processing
Table 6 Results obtained with WRE approach compared with the
. Command Error Rate depending on the weight reestimation rules (MLE, FFDW and FD) without ULT. 11 136 tests performed on VODIS corpus (noisy).
Compact Acoustic Models for Embedded Speech Recognition
Very compact model
Back to article page