Simon/Contribute Data: Difference between revisions
Created page with "To build a speech recognition system, several types of data files are required: * A phonetic dictionary to learn how words are pronounced * Transcribed audio samples to learn ..." |
(No difference)
|
Revision as of 14:20, 10 August 2013
To build a speech recognition system, several types of data files are required:
- A phonetic dictionary to learn how words are pronounced
- Transcribed audio samples to learn how a human pronounces the phonetic elements from the dictionary (phones)
- Large corpora of written text to learn what word structures commonly co-occur (provides context for the recognizer)