Proceedings of the 4th International Conference on Modern Education and Information Management, ICMEIM 2023, September 8–10, 2023, Wuhan, China

Research Article

The Application of Intelligent Speech Recognition Technology in the Comparison between Japanese and Manchu-Tungus Language

Download109 downloads
  • @INPROCEEDINGS{10.4108/eai.8-9-2023.2340188,
        author={Hongfang  Duan and Hexin  Wang},
        title={The Application of Intelligent Speech Recognition Technology in the Comparison between Japanese and Manchu-Tungus Language},
        proceedings={Proceedings of the 4th International Conference on Modern Education and Information Management, ICMEIM 2023, September 8--10, 2023, Wuhan, China},
        publisher={EAI},
        proceedings_a={ICMEIM},
        year={2023},
        month={11},
        keywords={speech recognition; manchu-tungus language; contrastive analysis},
        doi={10.4108/eai.8-9-2023.2340188}
    }
    
  • Hongfang Duan
    Hexin Wang
    Year: 2023
    The Application of Intelligent Speech Recognition Technology in the Comparison between Japanese and Manchu-Tungus Language
    ICMEIM
    EAI
    DOI: 10.4108/eai.8-9-2023.2340188
Hongfang Duan1,*, Hexin Wang1
  • 1: HeiLongJiang University of Technology
*Contact email: duanhongfang1983@163.com

Abstract

In order to understand the application of comparison between Japanese and Manchu-Tungus language, the application research of an intelligent speech recognition technology in comparison between Japanese and Manchu-Tungus language is put forward. In this paper, the development of intelligent speech recognition technology is briefly introduced, and the concept of intelligent speech interaction is introduced. Secondly, the comparison between Japanese and Manchu-Tungus language is described. It can be seen that the homology of third person pronouns and demonstrative pronouns is universal to some extent. It is not only a feature of Japanese and Manchu-Tungus language, but also a common form in Japanese dialects. Finally, the intelligent speech recognition system and its application analysis are summarized. When the voice information of the detected individual changes greatly with the change of the external environment, the system can identify the voice-related information in the shortest time, and identify the maximum probability of the state transition of the voice information. Then use the relevant sample content of the database to make a deeper analysis and judgment on the voice model of the detected person.