Signal Recognition for English Speech Translation Based on Improved Wavelet Denoising Method

Abstract

The signal corresponding to English speech contains a lot of redundant information and environmental interference information, which will produce a lot of distortion in the process of English speech translation signal recognition. Based on this, a large number of studies focus on encoding and processing English speech, so as to achieve high-precision speech recognition. The traditional wavelet denoising algorithm plays an obvious role in the recognition of English speech translation signals, which mainly depends on the excellent local time-frequency domain characteristics of the wavelet signal algorithm, but the traditional wavelet signal algorithm is still difficult to select the recognition threshold, and the recognition accuracy is easy to be affected. Based on this, this paper will improve the traditional wavelet denoising algorithm, abandon the single-threshold judgment of the original traditional algorithm, innovatively adopt the combination of soft threshold and hard threshold, further solve the distortion problem of the denoising algorithm in the process of English speech translation signal recognition, improve the signal-to-noise ratio of English speech recognition, and further reduce the root mean square error of the signal. Good noise reduction effect is realized, and the accuracy of speech recognition is improved. In the experiment, the algorithm is compared with the traditional algorithm based on MATLAB simulation software. The simulation results are consistent with the actual theoretical results. At the same time, the algorithm proposed in this paper has obvious advantages in the recognition accuracy of English speech translation signals, which reflects the superiority and practical value of the algorithm.

Research on the Reform of the Teaching Mode of Rural English Education Assistance Based on the Technical Support of Network Technology

“…After the original speech signal is pre-processed by noise reduction and other pre-processing, the first step is to extract features from speech data. From the existing research literature, it can be found that at this stage, acoustic feature extraction mainly adopts the Hidden Markov Chain for pattern recognition of the collected digital speech sequences, i.e., to realize the primitive classification of digital speech sequences [25][26].…”

The Construction of English Translation Teaching System in Colleges and Universities Based on Cluster Search Algorithm

“…Zhao, X. et al combined artificial intelligence with English machine translation, which innovated the English translation teaching mode, and promoted the development of the language education industry [15]. Chen, Z. used the improved wavelet denoising algorithm to recognize the English speech translation signals as a way of realizing high-precision English translation speech recognition, and solved the distortion situation in the recognition process of English speech translation signal, enhanced the recognition ability of English speech, and provided effective English speech for college students to learn English translation [16]. Karasaliu, A. analyzed the problems and difficulties in the process of English translation teaching and verified based on the data of students' questionnaires that teachers attitudes in carrying out English translation Teachers' attitudes in conducting English translation will affect students' ability to learn English translation, and there will be a certain gap in students' attitudes towards English translation teaching [17].…”

Research on Intelligent Recognition Model of English Translation Based on Nonlinear Dimensionality Reduction IC Features

“…Guo proposed a fuzzy algorithm to improve the performance of the English translation system by using the DNN-HMM speech recognition model and the traditional GMM-HMM speech recognition model to corpus and apply a small amount of training data to synthesize the information [15]. Chen used an improved wavelet denoising method for language recognition and used coding processing for English speakers, which effectively improved the recognition rate of speech and the accuracy of translation [16]. Ban and Ning studied Chinese-English machine translation based on deep neural networks, and the study showed that deep neural networks effectively improved the performance of translation and the system had higher usability [17].…”