Connected-Digit Speaker-Dependent Speech Recognition Using a Neural Network with Time-Delayed Connections

An analog neural network that can be taught to recognize stimulus sequences has been used to recognize the digits in connected speech. The circuit computes in the analog domain, using linear circuits for signal filtering and nonlinear circuits for simple decisions, feature extraction, and noise suppression. An analog perceptron learning rule is used to organize the subset of connections used in the circuit that are specific to the chosen vocabulary. Computer simulations of the learning algorithm and circuit demonstrate recognition scores >99% for a single speaker connected-digit data base. There is no clock; the circuit is data driven, and there is no necessity for endpoint detection or segmentation of the speech signal during recognition. Training in the presence of noise provides noise immunity up to the trained level. For the speech problem studied here, the circuit connections need only be accurate to about 3-b digitization depth for optimum performance. The algorithm used maps efficiently onto analog neural network hard-ware: single chip microelectronic circuits based upon this algorithm can probably be built with current technology.