Automatic Detection of [T] Pronunciation Errors for Chinese Learners of English

نویسندگان

  • Keelan Evanini
  • Becky Huang
چکیده

This study examines the types of errors produced by Chinese learners of English when attempting to pronounce [T] in reading passages and presents a system for automatically detecting these pronunciation errors. The system achieves an accuracy of 79.8%, compared to the inter-annotator exact agreement rate of 83.1%. In addition, speaker-level scores based on the total number of correct productions of [T] made by each speaker are generated from both the human and machine error annotations, and these are shown to have a strong correlation with each other (0.797).

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Development of Automatic Speech Recognition and Synthesis Technologies to Support Chinese Learners of English: The CUHK Experience

This paper presents our group’s ongoing research in the area of computer-aided pronunciation training (CAPT) for Chinese learners of English. Our goal is to develop technologies in automatic speech recognition (ASR) to support productive training for learners. We focus on modeling possible errors due to negative transfer from L1 (i.e. Chinese) of Chinese learners to L2 (English). ASR techniques...

متن کامل

Empathy as a Predictor of Pronunciation Mastery: The Case of Female Iranian EFL Learners’ Pronunciation Errors

The present study set out to identify the problematic areas of pronunciation among Iranian female EFL learners. Further, this study investigated the relationship between empathy and authentic pronunciation, along with gender as a moderator variable. Comparing segmental features and phonological processes of both languages helped teachers to predict the target errors. To reach such a goa...

متن کامل

Landmark-Based Pronunciation Error Identification on Chinese Learning

This paper explores a novel approach of identifying pronunciation errors for the second language (L2) learners based on the landmark theory of human speech perception. Earlier works on the selection method of distinctive features and the likelihoodbased “goodness of pronunciation” (GOP) measurement have gained progress in several L2 languages, e.g. Dutch and English. However, the improvement of...

متن کامل

A prototype of an adaptive Chinese pronunciation training system

Many beginning-level Chinese learners, particularly those whose mother tongue is not a tone language find it challenging to learn Chinese pronunciations and tones. Yet pronunciation practice in formal language class settings is limited. Therefore, it has become necessary to develop computer-assisted and adaptive training systems to help learners practice Chinese pronunciation outside of class. ...

متن کامل

Automatic detection and correction of non-native English pronunciations

Improving the feedback quality of a computer-based system for pronunciation training requires rather detailed and precise knowledge about the place and the nature of actual mispronunciations in a student’s utterance. To be able to provide this kind of information, components for the automatic localization and correction of pronunciation errors have been developed. This work was part of a projec...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012