신경회로망을 이용한 음성 인식 연구 = A Study on the Speech Recognition Using Neural Network

다국어 초록 (Multilingual Abstract)

This paper is study on the speech recognition using neural network. The used neural network in this paper are fuzzy ARTMAP(adaptive resonance theory mapping) and MLP(Multi-Layer Perceptron). The speech signals used for the purpose of evaluation in this study were taken from the phonemes in Korean digits uttered by six men. The test results show that fuzzy ARTMAP is a little better performance than MLP, when test data and training data is obtained from same speaker. But fuzzy ARTMAP is better performance than MLP, when test data and training data is obtained from different speaker. This result means that fuzzy ARTMAP is more useful to speaker adaptation and speaker-independent speech recognition than MLP.

목차 (Table of Contents)

• Ⅰ. 서 론
• Ⅱ. 음성 인식
• Ⅲ. 신경 회로망
• 1. MLP
• 2. 퍼지 ARTMAP
• Ⅳ. 실험 결과 및 고찰
• 1. 퍼지 ARTMAP을 이용한 인식 결과고찰
• 2. 퍼지 ARTMAP과 MLP을 이용한 인식 결과고찰
• Ⅴ. 결론
• 참고문헌