L2 Mispronunciation Verification Based on Acoustic Phone Embedding and Siamese Networks

Xie, Yanlu; Wang, Zhenyu; Fu, Kaiqi

doi:10.1007/s11265-020-01598-z

Cited by 3 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huang et al adopted the Maximum Likelihood Linear Regression (MLLR) to adjust the acoustic model which can reduce the mismatch between native original model and adaptive data from non-native speakers [2]. Xie et al introduced the phone grouping technique for mispronunciation detection based on mistakes probability [3]. Many researchers have also begun to apply Deep Neural Network (DNN) [4][5][6] to the pronunciation error detection of L2 (second language) learners, significantly improving the accuracy of pronunciation error detection.…”

Section: Related Workmentioning

confidence: 99%

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features

Huang

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

As a universal language, English has been paid more and more attention, among which oral English learning is very important. In this paper, the two key technologies of pronunciation error detection and quality evaluation are studied, both of them are effectively integrated, aiming to build a model for L2 learners’ English pronunciation quality evaluation. This paper mainly studies two different methods of pronunciation error detection. Based on the speech recognition framework, the standard score is compared with the threshold to judge the correctness of phoneme pronunciation, and the phoneme-dependent threshold is set to improve the maximum Precision to 0.44. By judging the correct pronunciation and confusing phoneme, the accuracy of pronunciation error detection is improved to 81.26%. This paper proposes the fusion algorithm from multi-dimensions of speech fluency and intonation respectively, and a newly designed feature called word duration ratio, which significantly improve the correlation of pronunciation quality evaluation to 0.746.

show abstract

Section: Related Workmentioning

confidence: 99%

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features

Huang

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

Mispronunciation detection and diagnosis using deep neural networks: a systematic review

Lounis,

Dendani,

Bahi

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Construction of network mathematics model for college English mixed teaching

Chen,

Tian

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

To better carry out college English blended teaching and make students adapt better, author Z proposes a method of college English blended teaching model based on the Internet of Things network platform. According to the development of today’s Internet of Things technology, this method combines English learning and the use of cloud computing to develop the Internet network platform, so it is suitable for professionals teaching in college to complete English education., thus improving the quality of education. According to the test results: the average score of 4th grade online students is 523, 78.3% scored above 425; The average score of 4th graders in the non-network course was 394, and 62.4% scored above 425. The 4th-grade score for the online course was 129 points higher than the average score nia average for the offline course and 15.9% higher than the average score of 425. Conclusion: The author’s approach can contribute to the creation of mixed English courses in colleges and universities sad.

show abstract

L2 Mispronunciation Verification Based on Acoustic Phone Embedding and Siamese Networks

Cited by 3 publications

References 39 publications

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features

Mispronunciation detection and diagnosis using deep neural networks: a systematic review

Construction of network mathematics model for college English mixed teaching

Contact Info

Product

Resources

About