We experienced that time could have been saved if many of the files we generated by HTK scripts had been written by hand. Both types of models seamed to work after a lot of time and pretty much help from colleagues that have previous experience from working with HTK. Two of us tried to model words as single units while one of used models on the phoneme level. All three of us followed the tutorial individually with the minimal vocabulary "one", "two" and "three". Our initial goal was to build a simple recognizer trained on a single user. Speech recognition In order to learn more about speech recognition, we installed the HTK toolkit and followed the tutorial as well as we could.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |