Ke Yan

Work place: USTC iFlytek Speech Laboratory, University of Science and Technology of China, Hefei, China



Research Interests: Natural Language Processing, Speech Synthesis


Ke Yan was born in Chengdu, China in 1984. He is a Ph.D. candidate at USTC (university of science and technology of China) and received his master’s degree on speech signal processing in 2009.
His research topics are computer assisted language learning. He did a series of pioneering researches on text-indepe d developed automatic recitation, retelling and translation evaluation systems for Chinese English learners (L2 learners). He also helps to improve the automatic PSC system.

Author Articles
Pronunciation Proficiency Evaluation based on Discriminatively Refined Acoustic Models

By Ke Yan Shu Gong

DOI:, Pub. Date: 8 Mar. 2011

The popular MLE (Maximum Likelihood Estimation) is a generative approach for acoustic modeling and ignores the information of other phones during training stage. Therefore, the MLE-trained acoustic models are confusable and unable to distinguish confusing phones well. This paper introduces discriminative measures of minimum phone/word error (MPE/MWE) to refine acoustic models to deal with the problem. Experiments on the database of 498 people’s live Putonghua test indicate that: 1) Refined acoustic models are more distinguishable than conventional MLE ones; 2) Even though training and test are mismatch, they still perform significantly better than MLE ones in pronunciation proficiency evaluation. The final performance has approximately 4.5% relative improvement.

[...] Read more.
Other Articles