Julius Open source speech recognition engine

Open source speech recognition software HTK, Julius and Kaldi and other systems know better

I. Installation by Source Tarball

Installation process is simple and contains the following points:

1. Download the newest source tarbal from Julius official Site–link
2. Unpack the archive For example to your user home directory
3. Configure and install Julius by following commands:

<span style= "Color:rgb (122, 8, 116); ><strong>cd</strong></span> ~<span style= "font-weight:bold;" >/</span>julius-4.2.2<span style= "Font-weight:bold;" >/</span> <span style= "Color:rgb (194, 12, 185); ><strong>sudo</strong></span>. <span style= "Font-weight:bold;" >/</span>configure <span style= "Color:rgb (194, 12, 185); ><strong>sudo</strong></span> <span style= "Color:rgb (194, 12, 185); ><strong>make</strong></span> <span style= "Color:rgb (194, 12, 185); ><strong>sudo</strong></span> <span style= "Color:rgb (194, 12, 185); ><strong>make</strong></span> <span style= "Color:rgb (194, 12, 185); ><strong>install</strong></span>

Two. Installation using Apt-get in Ubuntu do not install with sudo apt-get install Julius this way, install the old version, there will be some problems.

4. Try it by typing on command line:

julius-4.2.1 <span style= "font-weight:bold;" >//</span>output Julius rev.4.2.2-based on juliuslib rev.4.2.2 <span style= "Color:rgb (122, 8, 116);" ><strong> (</strong></span>fast<span style= "Color:rgb (122, 8, 116);" ><strong>) </strong></span> built <span style= "font-weight:bold;" >for</span> i686-pc-linux Copyright <span style= "Color:rgb (122, 8, 116); ><strong> (</strong></span>c<span style= "Color:rgb (122, 8, 116);" ><strong>) </strong></span> 1991-2012 Kawahara Lab, Kyoto University Copyright <span style= " Color:rgb (122, 8, 116); " ><strong> (</strong></span>c<span style= "Color:rgb (122, 8, 116);" ><strong>) </strong></span> 1997-2000 information-technology Promotion Agency, Japan Copyright <span style= "Color:rgb (122, 8, 116); ><strong> (</strong></span>c<span style= "Color:rgb (122, 8, 116);"><strong>) </strong></span> 2000-2005 Shikano Lab., Nara Institute of science and technology Copyright <span style= "Color:rgb (122, 8, 116); ><strong> (</strong></span>c<span style= "Color:rgb (122, 8, 116);" ><strong>) </strong></span> 2005-2012 Julius project team, Nagoya Institute of technology Try &LT;SP An style= "Color:rgb (255, 0, 0); > '-setting ' </span> <span style= "font-weight:bold;" >for</span> built-in engine configuration. Try <span style= "Color:rgb (255, 0, 0); > '-help ' </span> <span style= "font-weight:bold;" >for</span> run <span style= "Font-weight:bold;" >time</span> options.

5. Last additional thing needed to run Julius smoothly are a julius-voxforge package which can being installed via Apt-get by Typing in command line:

<span style= "Color:rgb (194, 12, 185); ><strong>sudo</strong></span> <span style= "Color:rgb (194, 12, 185); ><strong>apt-get install</strong></span> Julius-voxforge

That's all now you can start to configure it, because it's not coming configured just out of the box. I'll write a post in next few days about the basic configuration to which link'll be is added here.

Precautions:

The commands in 1.readme have changed:

sudo mkdfa.pl sample

Export Tmp=/tmp

Using Julius to build a speech recognition engine here is the dictation program, which can be used for a continuous speech recognition, and mainly for Chinese:

I. Basic structure of the speech recognition engine

Basic all the open source speech recognition engine is the following structure, including: Sphinx,julius, and so on, the following mainly take Julius as an example, explain the relevant content:

1.Acoustic model (Acoustic model): Used for the identification of phonemes.

The technology used:

1) HMM (Hiden Mokov Model):

2) GMM (Gaussian Mixture Model):

3) Dfa&nfa:

Build your own acoustic model:

The tools you can use:

2.Phoneme Dictionary (pronunciation dictionary): used for the recognition of words.

Build Your own pronunciation dictionary:

The tools you can use:

3.Language model: Used for recognition of statements.

Build Your own pronunciation dictionary:

The tools you can use:

The above three 3=>2=>1 in turn into a dependency, as long as the above three are configured, a speech recognition engine is set up, the other is to use the development package to provide APIs for custom development.

Two. Specific operation

Taking sample of Julius-voxforge as an example, the use of Julius mainly involves three files:

1.sample.grammar: Language grammar.

2. Sample.voca: Pronunciation dictionary.

3. julian.jconf: The primary configuration file for the speech recognition engine. Here you specify the three main elements of face reading.

As for other documents:

Sample.dfa

Sample.dict

Sample.term

are automatically generated---mkdfa.pl sample by command.