Open AdrianBZG opened 7 years ago
Implementing an voice-to-text recognition, after that we'll apply a filter to compare the generated text against the possible "predefined" actions over the scene, probably with a string distance algorithm (Hamming algorithm?).
Possible max number of predefined actions: 4
Sphinx added b195871
To change the used dictionary to Spanish:
Script: Assets/Scripts/SpeechRecognizerDemo.cs
// Code // Set path to acoustic model. configuration.setAcousticModelPath("resource:/edu/cmu/sphinx/models/es-es/es-es"); // Set path to dictionary. configuration.setDictionaryPath("resource:/edu/cmu/sphinx/models/es-es/cmudict-es-es.dict"); // Set language model. configuration.setLanguageModelPath("resource:/edu/cmu/sphinx/models/es-es/es-es.lm.bin");
More info: https://sourceforge.net/p/cmusphinx/discussion/sphinx4/thread/7d14eca1/
Implement Voice Recognition for certain actions Actions like: