As one of the four major skills in English learning,speaking is an important part in English learning which getting more and more attention.The study set out to improve the accuracy of speech recognition by applying s...As one of the four major skills in English learning,speaking is an important part in English learning which getting more and more attention.The study set out to improve the accuracy of speech recognition by applying speech recognition technology to the evaluation of English pronunciation.On this basis,the study attempts to improve computer speech evaluation methods.This model employs indexes such as intonation,speech rate,rhythm and intonation,using multi-dimensional indicators as evaluation criteria to establish a more comprehensive and objective English speech evaluation model.English learners can use the evaluation systems to guide their self-study,and the system can have a profound influence on the practice of teaching spoken English.展开更多
A stronger canonical model was developed to improve the performance of automatic pronunciation evaluations. Three different strategies were investigated with speaker adaptive training to normalize variations among spe...A stronger canonical model was developed to improve the performance of automatic pronunciation evaluations. Three different strategies were investigated with speaker adaptive training to normalize variations among speakers, minimum phone error training to identify easily confused phones and maximum likelihood linear regression （MLLR） adaptation to compensate for accent variations between native and non-native speakers. The three schemes were combined to improve the correlation coefficient between machine scores and human scores from 0.651 to 0.679 on the sentence level and from 0.788 to 0.822 on the speaker level.展开更多
基金supported by the Undergraduate Innovation Training Project of Guangdong University of Foreign Studies in 2020.
文摘As one of the four major skills in English learning,speaking is an important part in English learning which getting more and more attention.The study set out to improve the accuracy of speech recognition by applying speech recognition technology to the evaluation of English pronunciation.On this basis,the study attempts to improve computer speech evaluation methods.This model employs indexes such as intonation,speech rate,rhythm and intonation,using multi-dimensional indicators as evaluation criteria to establish a more comprehensive and objective English speech evaluation model.English learners can use the evaluation systems to guide their self-study,and the system can have a profound influence on the practice of teaching spoken English.
基金Supported by the National High-Tech Research and Development (863) Program of China (No. 2008AA01Z118)
文摘A stronger canonical model was developed to improve the performance of automatic pronunciation evaluations. Three different strategies were investigated with speaker adaptive training to normalize variations among speakers, minimum phone error training to identify easily confused phones and maximum likelihood linear regression （MLLR） adaptation to compensate for accent variations between native and non-native speakers. The three schemes were combined to improve the correlation coefficient between machine scores and human scores from 0.651 to 0.679 on the sentence level and from 0.788 to 0.822 on the speaker level.
