More importantly, L2 teachers are scarce in China, especially in the central and western regions where educational resources are insufficient. In addition, this face-to-face teaching mode is limited by many external objective conditions, such as time and place. Currently, L2 oral language teaching is teacher-centered and still uses the traditional one-to-many teaching model like other subjects, ignoring the development of students’ independent learning ability. As it is well known, the purpose of language is to communicate, while mastering a language necessarily requires learning its spoken pronunciation. More and more people are eager to learn another language (Second Language, L2) in addition to their native language, which in turn gives them an advantage in their study, life, and work. In the context of the comprehensive development of economic globalization and the continuous promotion of China’s opening-up process, communication between countries around the world is intensifying. The experimental results indicate that the designed system achieves a high accuracy of English pronunciation detection. Finally, the extracted 39 Mel Frequency Cepstral Coefficient (MFCC) acoustic features are used as the input of the improved random forest classifier to construct a classification error detection model. Furthermore, a forest decision tree is constructed using the reduced-dimensional feature-based data to improve the pronunciation detection accuracy. The distribution rules of the pronunciation data are extracted layer by layer by stacking deep SDAEs, and the coefficient penalties and reconstruction errors of each coding layer are combined to identify the features associated with the wrong pronunciation in the high-dimensional data. The algorithm inputs rare mispronunciation data into a GAN neural network to generate new class samples and improve the uneven distribution of mispronunciation data in the sample set. Then an improved random forest detection algorithm is designed. Firstly, a speech corpus is constructed along with the evaluation of the acoustic features. With the aim of solving this problem, the paper proposes an English pronunciation error detection system based on improved random forest. The existing English pronunciation error detection methods are more oriented to the detection of wrong pronunciation, and lack of targeted improvement suggestions for pronunciation errors.
0 kommentar(er)
