Speech recognition in English cultural promotion via recurrent neural network

Abstract

With the rapid development of artificial intelligence, English is the most widely used language in the world, and English speech recognition has become one of the hot spots in the field of artificial intelligence. In order to promote English culture accurately, this paper uses recurrent neural network and convolutional neural network to recognize the tone and tone color of English comprehensively and studies the optimal number of layers and neuron nodes when the recognition accuracy is highest. When the number of layers is 7 and the number of nodes is 256, the recognition accuracy is the highest, reaching 98%. It provides convenience for English teaching and further promotes the spread of English culture.