Skip to main content

Table 2 Settings for the ASR back-end

From: Strategies for distant speech recognitionin reverberant environments

Input features
40 log mel filterbank coefficients + Δ + Δ Δ (120 coef.)
Global mean and variance normalization + utterance level CMN
5 left and 5 right context (11 frames)
Acoustic model
DNN-HMM
7 hidden layers, 2048 hidden units,
1320 visible units, 3129 output units (HMM states)
Training data
(1) Baseline multi-condition training data (17h)
(2) Extended multi-condition training data (85h)
Language model
TRI : Trigram language model available with the WSJ corpus [28]
RNNLM : RNN-based language model (interpolation coef. 0.5)
Decoding parameters
Language model weight:11
Beam: 400