testing simon

A few seconds ago:

ubuntu@ubuntu-desktop:~/Documents/201005/speech2text$ git pull origin masterremote: Counting objects: 17, done.
remote: Compressing objects: 100% (9/9), done.
remote: Total 9 (delta 8), reused 0 (delta 0)
Unpacking objects: 100% (9/9), done.
From git://speech2text.git.sourceforge.net/gitroot/speech2text/speech2text
* branch master -> FETCH_HEAD
Updating afe2203..5853434
Fast-forward
simon/model/phonemes | 1 +
.../src/simonmodelmanagementui/ImportDict/dict.cpp | 3 ---
2 files changed, 1 insertions(+), 3 deletions(-)
ubuntu@ubuntu-desktop:~/Documents/201005/speech2text$ ./build_ubuntu.sh

Let’s take a look into sam:

1. Sorting is now working. Thanks for fixing that issue.
2. But the Edit sample button seems to be broken now.

I imported the words Hochkulturen (with IPA-[χ]) and Hochkultur (with ASCII-[x]), but only the word Hochkultur is being displayed:

After importing the words Hochkulturen (with UTF-8-[χ]) and Hochkultur (with ASCII-[x]), only one word remains. Obviously, the other word Hochkulturen has been omitted by simon. Maybe this is a simon security precaution.

This is what I did a few minutes ago because sorting has been fixed and because of the symbol [χ]:

ubuntu@ubuntu-desktop:~$ cd Documents/201005/speech2text && git pull origin master
remote: Counting objects: 35, done.
remote: Compressing objects: 100% (18/18), done.
remote: Total 18 (delta 15), reused 0 (delta 0)
Unpacking objects: 100% (18/18), done.
From git://speech2text.git.sourceforge.net/gitroot/speech2text/speech2text
* branch master -> FETCH_HEAD
Updating 97be4d2..afe2203
Fast-forward
sam/src/samview.cpp | 1 +
.../src/simonmodelmanagementui/ImportDict/dict.cpp | 3 +++
simonlib/simonmodeltest/fileresultmodel.cpp | 7 +++++--
3 files changed, 9 insertions(+), 2 deletions(-)
ubuntu@ubuntu-desktop:~/Documents/201005/speech2text$ ./build_ubuntu.sh

I want to see whether the Ach-Laut is imported correctly by importing these entries (first entry with ASCII-[x]; second entry with IPA-[χ]:

<lexeme role="Substantiv">
<grapheme>Hochkultur</grapheme>
<phoneme>hoːxkʊltuːʀ</phoneme>
<phoneme>hoːxkʊltuːɐ̯</phoneme>
</lexeme>
<lexeme role="Substantiv">
<grapheme>Hochkulturen</grapheme>
<phoneme>hoːχkʊltuːʀən</phoneme>
<phoneme>hoːχkʊltuːɐ̯n</phoneme>
</lexeme>

No, it didn’t work out:

The word Hochkultur is displayed with the correct SAMPA. But the word Hochkulturen doesn’t have the correct SAMPA.

A few minutes ago, I deleted several files from the /home/ubuntu/.kde/share/config/ folder. Then I repeated steps 1 – 4. Then I pressed the following buttons: Connect – Synchronize – Activate. And then, this error message appeared:

Obviously, a lot of words beginning with the letter b are affected. I think that maybe something went wrong with section xdb.

I found the mistake: The file:///home/ubuntu/Documents/201006/audacity/xdb-folder/prompts-xdb contains wrong content. I will have to fix that.

It is working now.

I want to use Ralf’s German speech model version 0.1.4 as static model. Because my last try a few minutes ago was not successful, I am writing this detailed report:

1. Quit simon and ksimond.
2. Delete the folders file:///home/ubuntu/.kde/share/apps/simon and
file:///home/ubuntu/.kde/share/apps/simond with the following commands:

$ rm -i -r /home/ubuntu/.kde/share/apps/simon
$ rm -r /home/ubuntu/.kde/share/apps/simond

3. Start simon. Manage scenarios > Import > Import from file. I choose file:///home/ubuntu/Downloads/german-speech-model-0.1.4/scenario-0.1.4.xml.

4. Simon > Settings > Configure simon > Model settings > Static model. Load the following paths:
file:///home/ubuntu/Downloads/german-speech-model-0.1.4/hmmdefs-0.1.4
file:///home/ubuntu/Downloads/german-speech-model-0.1.4/tiedlist-0.1.4
file:///home/ubuntu/Downloads/german-speech-model-0.1.4/macros-0.1.4
file:///home/ubuntu/Downloads/german-speech-model-0.1.4/stats-0.1.4

Press Apply. Press OK.

5. Start ksimond.
simon > Connect button.
simon > Synchronize button.
simon > Activate button. Then the following error message appears:

Could not start recognition because the system reports that the recognition is not ready.

Please check if you have defined a vocabulary, an appropriate grammar and recorded a few trainings samples.

The system will then, upon synchronization, generate the model which will be used for the recognition

What went wrong? I had imported the scenario scenario-0.1.4.xml which includes a grammar (only the terminal Unknown), and the dictation plug-in. That should be sufficient. A vocabulary is available, too, of course.

Question: What went wrong?

At the moment, I am importing 21007 wav files into simon. I want to increase the amount of training data.

It takes a few minutes until all files are imported.

I hope that it will work as expected.

Edit: No, it just worked partially. Just about 862 words are contained in the file file:///home/ubuntu/.kde/share/apps/simond/models/default/active/model.dict. Why does simon use just this small subset?

Edit #2: I selected the “static model” option instead of “user generated model”. I will try again.

Edit #3: Obviously, I imported only a small dictionary. This means that the acoustic model has been trained with 21007 words, but the language model contains just 862 words.

Edit #4: I think that I found the mistake. The file file:///home/ubuntu/Documents/201008/lexicon-all.xml doesn’t contain valid XML code. I have to fix that, then I will try again.

Again, more German speech models:

Download German speech model 'xhb' (license: GPLv3)
Download German speech model 'xib' (license: GPLv3)
Download German speech model 'xjb' (license: GPLv3)
Download German speech model 'xoa' (license: GPLv3)
Download German speech model 'xpa' (license: GPLv3)
Download German speech model 'xpb' (license: GPLv3)
Download German speech model 'xpw' (license: GPLv3)

The speech models are derived from Ralf's German IPA FLAC files (xoa xpa xpb; external links: xhb xib xjb xpw).

Note: Most links in this article don’t work at the time of publication: “The server is temporarily unable to service your request due to maintenance downtime or capacity problems.” Sorry for that. I hope that this problem won’t occur too often.

More German speech models:

Download German speech model 'xja' (license: GPLv3)
Download German speech model 'xka' (license: GPLv3)
Download German speech model 'xla' (license: GPLv3)
Download German speech model 'xma' (license: GPLv3)
Download German speech model 'xna' (license: GPLv3)

The speech models are derived from Ralf's German IPA FLAC files (sections xja xka xla xma xna).

Here are more German speech models that you can import into simon:

Download German speech model 'xga' (license: GPLv3)
Download German speech model 'xgb' (license: GPLv3)
Download German speech model 'xgx' (license: GPLv3)
Download German speech model 'xha' (license: GPLv3)
Download German speech model 'xia' (license: GPLv3)

These speech models are derived from Ralf's German IPA FLAC files (sections xga xgb xgx xha xia).