An automatic speech recognition system on DSP board

Abstract

The research aims to design and implement an automatic speech recognition and synthesis system. A TMS320C6713 DSK Board manufactured by Texas Instrument (TI) is adopted as the system operation platform to support independent development, and the MATLAB software is adopted as the operation platform of the speech synthesis system. Moreover, the two platforms are integrated by a human machine interface development by Visual C#. The design of speech recognition system can be divided into two stages, training and recognition. In the stage, each input speech is matched with the reference speeches stored in the external memory in sequence, and the match with minimum distortion rate is the recognition result. The speech recognition system supports not only 85% average recognition rate, but also high portability for various digital speech control of robots.