<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In recent years, the development of artificial intelligence technology and theory has been rapid, and the application in language science has been gradually comprehensive and diversified, especially the accuracy rate of artificial intelligence for Chinese language is up to 90%. In the era of artificial intelligence, the effect of different structures and parameters of arithmetic models on Chinese language recognition varies greatly. Language science is an important research area for realizing machine-human communication, and accurate comprehension of the meaning of linguistic expressions is the key to realize communication. In this paper, we construct a speech system that is different from the traditional stable time series for the irreplaceable characteristics of artificial intelligence technology to improve Chinese language ability. A dynamic Bayesian network (DBN) is used for modeling and analysis, and a DBN construction method is investigated to import a hidden Markov model in a speech recognition system to reveal the interactions between nodes within multiple time slices. The accuracy of dynamic Bayesian networks in Chinese dialect inference algorithms is demonstrated using Matlab simulations to characterize the reliability of speech features using a speech spectrogram. It proves that artificial intelligence technology and Chinese language science are complementary and mutually reinforcing, showing a good and rapid development trend.</p>
</abstract>

In recent years, the development of artificial intelligence technology and theory has been rapid, and the application in language science has been gradually comprehensive and diversified, especially the accuracy rate of artificial intelligence for Chinese language is up to 90%. In the era of artificial intelligence, the effect of different structures and parameters of arithmetic models on Chinese language recognition varies greatly. Language science is an important research area for realizing machine-human communication, and accurate comprehension of the meaning of linguistic expressions is the key to realize communication. In this paper, we construct a speech system that is different from the traditional stable time series for the irreplaceable characteristics of artificial intelligence technology to improve Chinese language ability. A dynamic Bayesian network (DBN) is used for modeling and analysis, and a DBN construction method is investigated to import a hidden Markov model in a speech recognition system to reveal the interactions between nodes within multiple time slices. The accuracy of dynamic Bayesian networks in Chinese dialect inference algorithms is demonstrated using Matlab simulations to characterize the reliability of speech features using a speech spectrogram. It proves that artificial intelligence technology and Chinese language science are complementary and mutually reinforcing, showing a good and rapid development trend.

Strategies for improving Chinese language proficiency based on artificial intelligence technology

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In recent years, the development of artificial intelligence technology and theory has been rapid, and the application in language science has been gradually...

Strategies for improving Chinese language proficiency based on artificial intelligence technology

Online veröffentlicht: 28. Apr. 2023

Seitenbereich: -

Eingereicht: 29. Jan. 2022

Akzeptiert: 19. Juli 2022

DOI: https://doi.org/10.2478/amns.2023.1.00074

Schlüsselwörter
artificial intelligence, Chinese language system, dynamic Bayesian network, speech spectrogram, speech recognition

© 2023 Yuanyuan Sun, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Strategies for improving Chinese language proficiency based on artificial intelligence technology

Online veröffentlicht: 28. Apr. 2023

Seitenbereich: -

Eingereicht: 29. Jan. 2022

Akzeptiert: 19. Juli 2022

DOI: https://doi.org/10.2478/amns.2023.1.00074

Schlüsselwörterartificial intelligence, Chinese language system, dynamic Bayesian network, speech spectrogram, speech recognition

© 2023 Yuanyuan Sun, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
artificial intelligence, Chinese language system, dynamic Bayesian network, speech spectrogram, speech recognition