Tetsuro Kitazoe

Acoustic speech recognition method and system using stereo vision neural networks with competition and cooperation

A method and system are provided for speech recognition. The speech recognition method includes the steps of preparing training data representing acoustic parameters of each of phonemes at each time frame; receiving an input signal representing a sound to be recognized and converting the input signal to input data; comparing the input data at each frame with the training data of each of the phonemes to derive a similarity measure of the input data with respect to each of the phonemes; and processing the similarity measures obtained in the comparing step using a neural net model governing development of activities of plural cells to conduct speech recognition of the input signal. In the processing step, each cell is associated with one respective phoneme and one frame, a development of the activity of each cell at each frame in the neural net model is suppressed by the activities of other cells on the same frame corresponding to different phonemes, and the development of the activity of each cell at each frame being enhanced by the activities of other cells corresponding to the same phoneme at different frames. In the process, the phoneme of a cell that has developed the highest activity is determined as a winner at the corresponding frame to produce a list of winners at respective frames. A phoneme is outputted as a recognition result for the input signal in accordance with the list of the winners at the respective frames that have been determined in the step of processing.

Evolutionary robot controllers with competitive and cooperative neural networks

This article describes a new approach for control systems for an autonomous mobile robot by using sandwiches of two different types of neural network. One is a neural network with competition and cooperation, and is used for recognizing sensor information where synaptic coupling are fixed. The second is a neural network with adaptive synaptic couplings corresponding to a genotype in a creature, and used for self-learning for the wheel controls. In a computer simulation model, we were successful in obtaining four types of robot with good performance when going along a wall. The model also showed robustness in a real environment.

Control system for the Khepera robot by a neural network with competition and cooperation

This article describes a new approach to control systems for a mobile robot Khepera by using a neural network with competition and cooperation as the processing unit for the robot sensors. Competition makes only one neuron active, while cooperation keeps them all active. In our research, we find that the Khepera controlled by this neural network can maintain a smoother trajectory than when it is controlled by the output values of its own sensors, especially in noisy environments.

Speech recognition using a stereo vision neural network model

This paper describes a new algorithm for speech recognition by using stereo vision pattern recognition equations with competition and cooperation. In our research, we applied recently developed 3-layered neural net (3LNN) equations to speech recognition. Our proposed acoustic models using these equations yield better recognition results than the hidden Markov model (HMM). When using a 216 (240) word database, stereo vision acoustic models gave 6.5% (6.6%) higher accuracy than HMMs.

Application of a stereovision neural network to continuous speech recognition

The two- or three-layered neural networks (2LNN, 3LNN) which originated from stereovision neural networks are applied to speech recognition. To accommodate sequential data flow, we consider a window through which the new acoustic data enter and from which the final neural activities are output. Inside the window, a recurrent neural network develops neural activity toward a stable point. The process is called winner-take-all (WTA) with cooperation and competition. The resulting neural activities clearly showed recognition of continuous speech of a word. The string of phonemes obtained is compared with reference words by using a dynamic programming method. The resulting recognition rate was 96.7% for 100 words spoken by nine male speakers, compared with 97.9% by a hidden Markov model (HMM) with three states and a single gaussian distribution. These results, which are close to those of HMM, seem important because the architecture of the neural network is very simple, and the number of parameters in the neural net equations is small and fixed.