Artificial intelligent for speech reproduction of information and knowledge of ancient books

摘要

Artificial intelligent for speech reproduction of the information and knowledge of ancient books is discussed in this paper. The integrated retrieval of digital libraries has gone through several different development stages, including platform integration, system integration and the data integration. Among them, the data integration of literature is the most difficult and most critical. Therefore, in this paper, the feature extraction method based on deep learning domain is mainly expanded from two processing methods: convolution neural network structure and convolution cyclic neural network structure. At the same time, the feature extraction methods under the two methods are explained in detail in order to express the content of the text information more accurately and to obtain better classification effect. Besides this, the speech reproduction of information and knowledge is also integrated to improve the robustness of the model. The simulation results have pointed out the effectiveness.