speech recognition software

Schott’s General American dictionary 0.2

admin — Tue, 01 May 2012 16:46:50 +0000

About two years ago, I published Ralf’s General American dictionary version 0.1.1. I decided to develop the next version 0.2 of this dictionary from scratch. The dictionary gets a new name: Schott's General American dictionary instead of Ralf's General American dictionary. This article explains the creation of the dictionary:

1. Get an American English spelling dictionary with 390.000 words.

2. License is GPL version 2.
3. Encoding of the files en_US.dic and en_US.aff is UTF-8.
4. Linux Mint terminal:

cd /home/ubuntu/Documents/american-english
unmunch en_US.dic en_US.aff > american-wordlist

5. Add speak tags at the beginning and the end of american-wordlist.
6. Linux Mint terminal:

espeak -f american-speak-audio -m -v en-us -q -x --phonout="american-espeak"

7. Adding tags to the file american-espeak ( at the beginning of the file; at the end of the file).
8. Linux Mint terminal:

saxonb-xslt -ext:on -s:american-espeak -xsl:'http://spirit.blau.in/simon/files/2010/04/replace-newline-newline-space-by-phoneme-element.xsl' -o:american-phoneme-elements
mkdir espeak
paste american-speak-audio american-phoneme-elements > espeak/general-american-dictionary.xml

9. Download the dictionary (eSpeak edition).

10. I am planning to release an IPA version of this dictionary.

Ralf’s Canadian English dictionary 0.1

admin — Sat, 28 Apr 2012 14:29:37 +0000

This article explains the creation of Ralf’s Canadian English dictionary version 0.1.

1. Get a Canadian spelling dictionary with 390.000 words.
2. License is GPL.
3. Encoding of the files en_CA.dic and en_CA.aff is UTF-8.
4. Linux Mint terminal:

cd /home/ubuntu/Documents/canadian-english
unmunch en_CA.dic en_CA.aff > canadian-wordlist

5. Add tags at the beginning and at the end of canadian-wordlist.
6. Linux Mint terminal:

saxonb-xslt -ext:on -s:canadian-wordlist -xsl:'http://spirit.blau.in/simon/files/2010/04/create-audio-elements.xsl' -o:canadian-speak-audio
espeak -f canadian-speak-audio -m -v en -q -x --phonout="canadian-espeak"

7. Adding tags to the file canadian-espeak ( at the beginning of the file; at the end of the file).

8. Create elements:

saxonb-xslt -ext:on -s:canadian-espeak -xsl:'http://spirit.blau.in/simon/files/2010/04/replace-newline-newline-space-by-phoneme-element.xsl' -o:canadian-phoneme-elements

9. Combine and elements:

mkdir espeak
paste canadian-speak-audio canadian-phoneme-elements > espeak/canadian-english-dictionary.xml

10. Download the dictionary (eSpeak edition).

I am planning to create an IPA version of this dictionary.

Ralf’s British English dictionary 0.1

admin — Sat, 28 Apr 2012 13:00:45 +0000

This article explains the creation of a British English pronunciation dictionary.

1. Download the 390.000 words version of the dictionary.

2, License is GPL.
3. Linux Mint terminal:

cd /home/ubuntu/Documents/british

4. Now I install Geany because I want to check the encoding of the files en_GB.aff and en_GB.dic: sudo apt-get install geany
The encoding of both files is UTF-8.

5. Linux Mint terminal:

sudo apt-get install hunspell-tools
cd /home/ubuntu/Documents/british
unmunch en_GB.dic en_GB.aff > british-wordlist
sudo apt-get install espeak

I need to know which voice I should use.
Linux Mint terminal:

espeak --voices

I will use en-uk. What is the proper command? I had generated US English phonemes. The command was:

espeak -f english-grapheme -m -v en-us -q -x --phonout="english-espeak"

I will have to markup the dictionary file with speak and audio tags.

6. Now I install saxonb-xslt with the following command:

sudo apt-get install libsaxonb-java

7. Add speak tags at the beginning and at the end of the file british-wordlist.
8. Linux Mint terminal:

saxonb-xslt -ext:on -s:british-wordlist -xsl:'http://spirit.blau.in/simon/files/2010/04/create-audio-elements.xsl' -o:british-speak-audio
espeak -f british-speak-audio -m -v en-uk -q -x --phonout="british-espeak"

9. Adding tags to the file british-espeak ( at the beginning of the file; at the end of the file).

10. Create phoneme elements (compare with this article):

saxonb-xslt -ext:on -s:british-espeak -xsl:'http://spirit.blau.in/simon/files/2010/04/replace-newline-newline-space-by-phoneme-element.xsl' -o:british-phoneme-elements

11. Combine grapheme elements with phoneme elements:

paste british-speak-audio british-phoneme-elements > british-dictionary-espeak.xml

12. Download the dictionary (eSpeak edition).

I am planning to create an IPA version of this PLS dictionary.

Compare graphemes of two dictionaries

admin — Mon, 05 Dec 2011 13:31:17 +0000

Here is the concept of a script that can compare two dictionaries with each other. The first dictionary uses grapheme elements which are in upper case letters, the second dictionary distinguishes between upper case and lower case. If there is a corresponding entry in the second dictionary, the entry of the first dictionary will be set to lower case in the resulting output tree. Here is the script:

// Compare the grapheme elements of two dictionaries

if (file_exists(‘general-american-dictionary.xml’)) {
$xml = simplexml_load_file(‘general-american-dictionary.xml’);
$english = simplexml_load_file(‘english-dictionary.xml’);

foreach ($xml->lexeme as $lexeme) {
$grapheme = $lexeme->grapheme;
foreach ($english->lexeme as $lexemeenglish) {
$graphemeenglish = $lexemeenglish->grapheme;
if ($grapheme == strtoupper($graphemeenglish)) {
$grapheme = $graphemeenglish;
}
}
echo $grapheme, ‘ ‘, $lexeme->phoneme, PHP_EOL;
}
} else {
exit(‘Failed to open general-american-dictionary.xml.’);
}
?>

Of course, this script is not yet finished. This script is working very slow, but never mind.

What are amplitude, frequency, wavelength?

admin — Sun, 30 Aug 2009 18:50:14 +0000

I think that 16 kHz / 16 bit recordings should be sufficient for the development of a speech model. But what does that mean? A good article explains the differences between amplitude (16 bit recordings are more precise than 8 bit recordings), and frequency, wavelength (the human ear can distinguish up to 20 kHz; you need the double amount of kHz for recording; 16 kHz means that 8 kHz are distinguished – should be sufficient for speech).

Replacing HTK by Sphinx?

admin — Fri, 28 Aug 2009 22:45:07 +0000

You need to install HTK if you want to run simon with the whole functionality. HTK is not included, it has to be downloaded from a different source (registration required). From my point of view, this information could hint people who are familiar with Sphinx and Qt into the right direction:

“simon uses the NON-FREE HTK for that. Only _one_ class in simon comes into contact with the HTK. The model compilation manager. This class: http://speech2text.svn.sourceforge.net/viewvc/speech2text/trunk/simonlib…. Those 1200 lines (including other, julius related stuff) are everything that links simon to the HTK. The class could very, very easily be replaced with one that uses something else.”

simon should continue to make use of HTK because there are things that you never should do:

“They did it by making the single worst strategic mistake that any software company can make:

They decided to rewrite the code from scratch.”

Well, but maybe there is someone out there who would want to start a fork of simon, and replace HTK by Sphinx? Of course, this would be a completely different project.

I think that Sphinx could use a GUI.

Sound frames – a, e, i, o, u, b(e)

admin — Sat, 18 Jul 2009 10:49:11 +0000

Let’s take a look at a few sound frames (click picture to enlarge):

U+0061 (a), U+02D0
The sounds in this article correspond to the German pronunciation.

U+0065 (e), U+02D0

U+0069 (i), U+02D0

U+006F (o), U+02D0

U+0075 (u), U+02D0

First part: U+0062 (b) – second part: U+0065 (e), U+02D0

Julius package for Ubuntu

admin — Thu, 18 Jun 2009 17:49:13 +0000

Soon, there should be an updated Julius package for Ubuntu (4.0.2 -> 4.1.2).

Characteristics of the sound “a”

admin — Wed, 20 May 2009 01:37:45 +0000

Let’s take a look at the characteristics of the sound “a” (spoken like in father). Here is a screenshot of Audacity which shows the repetitive pattern of the sound “a”:

I have marked the different waves with numbers 1, 2, 3, 4, 5. The waves with the same number are slightly different one from another, but they are similar. It is a repetitive pattern. Let’s extract a complete frame of the sound “a”:

The above picture shows the first frame. Let’s compare the first frame with the second frame:

Take a look at the yellow marked area, and compare it with the corresponding area of the previous picture. It is slightly diffent.

This was a short introduction into signal processing. These sound waves can be analysed by software like the HTK toolkit.

Installing simon-juliusd-0.1-alpha2.exe

admin — Sun, 22 Jun 2008 07:19:33 +0000

I just downloaded the obviously recently released program simon-juliusd-0.1-alpha2.exe. Before running the program, I checked it with ClamWin (I always do that before I install new software). It is OK, so I will install this program on my computer. The program is licensed under the GPL. On my computer, the program simon.exe was installed on the location “H:\Program Files\simon\simon-0.1-alpha-2.”

Here is a screenshot:

But now, it is beginning to get complicated. Take a look at the next screenshot:

So to use this program successfully, there are several additional programs needed. I need the HTK toolkit, and Julius. And there are further components necessary. I think I will stop the installation now. Or should I continue? At the moment, I am not sure. I think, that I will hit the next button.

I won’t publish a screenshot from the next step. But it is about HTK programs HDman, HCopy, and several other programs. I think (but I am not sure) that it is necessary to tell Simon the path on which location those programs are installed. A few months ago, I made some first steps with HTK and Julius, but everything was pretty complicated. At the moment, I am reading a few pages in the HTK book, everything is very abstract. And it takes a lot of time to get involved. But it is possible! You just have to stay focused.