Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 4 BLSTM accuracy as a function of the number of layers

From: Advanced recurrent network-based hybrid acoustic models for low resource speech recognition

Model

# layers

 

2

3

4

BLSTM-fbank

48.9

48.3

48.5

BLSTM-MBN

43.9

43.8

44.8

Back to article page