PURPOSE: To secure a high recognition rate and to easily perform real-time processing by inputting the mean PARCOR coefficient of a voice to a neural network.
CONSTITUTION: The recognition system 1 is constituted by combining a PARCOR analysis part 10, averaging circuits 15, the neural network 20, and a decision circuit 30. Then when a word is recognized from an input voice by using the neural network 20, the mean PARCOR coefficient of the voice is inputted to the neural network 20. Therefore, preprocessing for obtaining the input becomes simpler than conventional complicate feature quantity extraction and the time required for the preprocessing is shortened. Consequently, the high recognition rate is secured and the real-time processing is easily performed.
NISHIMURA SHINGO
UNNO MASAYUKI
MIYAGAWA MASASHI
Next Patent: ANTIREFLECTION FILM FOR SYNTHETIC RESIN