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