14.6 Speech recognition network sample

This section introduces the sample including speech separation, recognition, and success rate evaluation. Although the samples are for off-line use, you can use it for online processing just replacing AudioStreamFromWave to AudioStreamFromMic . All sample files are in Recognition directory. See Table 14.20 for details. The rest of this section describes how to run the samples step-by-step.

Table 14.20: The list of files

Category

File name

Description

Data

MultiSpeech.wav

Wave file used in this sample

JuliusMFT

julius.jconf

Configuration file of JuliusMFT

 

hmmdefs.gz

Acoustic model

 

allTriphones

List of triphones in the acoustic model

 

order.*

Grammar-based language model

HARK

MultiSpeechRecog.n

HARK network file for localization, separation, and feature extraction

 

Recognition.sh

Shell script to run the network file

 

loc_tf.dat

Transfer function for localization

 

sep_tf.tff

Transfer function for separation

 

wav/

Directory for separated sounds

Evaluation

score.py

Evaluation script

 

transcription_list*.txt

Reference data of the utterances for each direction