Some words about the creation of Ralf’s Latvian speech model:
1. Get Ralf’s Latvian dictionary.
2. Create a Latvian scenario.
3. Import the dictionary as shadow dictionary into simon.
4. Now I want to train 10 Latvian words. Press the button Train selected words.
5. Simon is asking now:
Your vocabulary does not define all words used in this text. These words are missing:
jâpârkurc, Lauciene, laukumains, olimpiete, olimpiâde, piekliegt, satriecâs, uzpletâm, þûpîba, þûþas
Do you want to add them now?
Press the Yes button.
6. The Define word window opens. You don’t have to change anything here (you could, but you don’t have to). Simply press the Next button.
7. Please speak a word. The volume will be calibrated by Simon automatically. Press the Next button.
8. The recording volume is now correct. Press the Next button.
9. Now it is time to record the first Latvian word. Press the Record button.
10. Simon is recording the word. Press the Record button again. Then press the Next button.
11. The new word has been added. Press the Finish button.
12. Switch to the Grammar tab. Press the button Add sentence. Add as sentence the word “Unknown”.
13. Enter the new sentence structure. The structure is very simple: “Unknown”.
14. Switch to the Commands tab. Press the button Manage plugins.
15. Press the Add button. It is necessary to activate the dictation plugin.
16. Select Dictation.
17. Append text after result. Press the space-bar one time. This means that after each recognized word, there will be a space.
18. In the Menu, select Actions > Synchronize. After waiting a few moments, select Actions > Activate. Then dictate a few Latvian words:
jâpârkurc jâpârkurc þûþas þûpîba þûpîba piekliegt olimpiete þûpîba jâpârkurc jâpârkurc uzpletâm þûpîba þûþas
The recognition result is poor but better than just random.
19. Press the Manage scenarios button.
20. Select Export > Export to file.
21. Press Configure acoustic model.
22. Export active model.
23. Download Ralf’s Latvian speech model, and use it with Simon 0.3.80.
Tags: Latvian, speech model