Speech recognition system
First Claim
1. A speech recognition system, designed by an Application Specific Integrated Circuit (ASIC), inputting a speech signal and outputting a recognition result, and using modular design to divide the speech recognition system into four modules, and each of the four modules forming an intellectual product (IP) on its own, wherein the four modules including:
- a control module, receiving an external signal for controlling an internal circuit, and said external signal comprises a training button and a recognition button;
an autocorrelation and linear prediction module, comprising an autocorrelation unit and a linear predictive coefficient unit, and the two units individually finding the autocorrelation coefficient, and the linear predictive coefficient respectively, to convert the inputted speech data into linear predictive coefficient;
a cepstrum module, using said linear predictive coefficient to output the cepstrum for the speech data model;
a Dynamic Time Warping (DTW) module, using the DTW algorithm to analyze said speech data model and outputting a recognition result; and
, wherein the control module is connected to the autocorrelation and linear predictive coefficient module unidirectionally, that is signals only flow from the control module; and
the control module is connected to the cepstrum module and the DTW module bidirectionally and the autocorrelation and linear predictive coefficient module is connected to the cepstrum module unidirectionally, that is signals are transferred from the autocorrelation and linear predictive module to the cepstrum module.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention discloses a complete speech recognition system having a training button and a recognition button, and the whole system uses the application specific integrated circuit (ASIC) architecture for the design, and also uses the modular design to divide the speech processing into 4 modules: system control module, autocorrelation and linear predictive coefficient module, cepstrum module, and DTW recognition module. Each module forms an intellectual product (IP) component by itself. Each IP component can work with various products and application requirements for the design reuse to greatly shorten the time to market.
-
Citations
10 Claims
-
1. A speech recognition system, designed by an Application Specific Integrated Circuit (ASIC), inputting a speech signal and outputting a recognition result, and using modular design to divide the speech recognition system into four modules, and each of the four modules forming an intellectual product (IP) on its own, wherein the four modules including:
- a control module, receiving an external signal for controlling an internal circuit, and said external signal comprises a training button and a recognition button;
an autocorrelation and linear prediction module, comprising an autocorrelation unit and a linear predictive coefficient unit, and the two units individually finding the autocorrelation coefficient, and the linear predictive coefficient respectively, to convert the inputted speech data into linear predictive coefficient;
a cepstrum module, using said linear predictive coefficient to output the cepstrum for the speech data model;
a Dynamic Time Warping (DTW) module, using the DTW algorithm to analyze said speech data model and outputting a recognition result; and
, wherein the control module is connected to the autocorrelation and linear predictive coefficient module unidirectionally, that is signals only flow from the control module; and
the control module is connected to the cepstrum module and the DTW module bidirectionally and the autocorrelation and linear predictive coefficient module is connected to the cepstrum module unidirectionally, that is signals are transferred from the autocorrelation and linear predictive module to the cepstrum module. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
- a control module, receiving an external signal for controlling an internal circuit, and said external signal comprises a training button and a recognition button;
Specification