In this study, we propose a discriminative training algorithm to jointly minimize mispronunciation detection errors (i.e., false rejection and false acceptances) and diagnosis errors (i.e., correctly pinpointing mispronunciations but incorrectly stating how they are wrong). An optimization procedure, similar to Minimum Word Error (MWE) discriminative training, is developed to refine the ML-trai...

Julia Brody, Ph.D., Executive Director, Silent Spring Institute Kenneth P. Cantor, Ph.D., M.P.H., Senior Investigator, Division of Cancer Epidemiology and Genetics, National Cancer Institute William L. Chameides, Ph.D., Dean, Nicholas School of the Environment, Duke University Capt. Susan M. Conrath, Ph.D., U.S. Public Health Service, Office of Air and Radiation, Indoor Environments Division, U...

To the Editor, "Indian Medical Gazette." Sir,?In the communication from Surgn.-Capt. P. W. O'Gorman in your issue for November regarding hda azar I see no mention of the fact of his having made use of the microscope in his search for anchylostomata. If, instead of straining the motion and examining them microscopically, he examines them microscopically according to the directions given by Sonsi...

In recent years, Computer Assisted Pronunciation Technology (CAPT) systems have been developed that can help Japanese learners to study foreign languages. We have been developing a pronunciation training system to evaluate and correct learner's pronunciation by extracting articulatory-features (AFs). In this paper, we propose a novel pronunciation training system that can plot the place and man...

This study demonstrates how knowledge of language transfer can enable a computer-assisted pronunciation teaching (CAPT) system to effectively detect and diagnose salient mispronunciations in second language learners’ speech. Our approach uses a HMM-based speech recognizer with an extended pronunciation lexicon that includes both a model pronunciation for each word and common pronunciation varia...

The paper analyzes the interaction between humans and computers in terms of response time in solving the image-based CAPT-CHA. In particular, the analysis focuses on the attitude of the different Internet users in easily solving four different types of image-based CAPTCHAs which include facial expressions like: animated character, old woman, surprised face, worried face. To pursue this goal, an...

are strictly accurate. I have now done over 800 cataracts by my method, and over 1,200 cataracts altogether (including the 800) since October 1911. This number is large enough to give me confidence both in my conclusions and in my ability to reply to his criticisms. Capt. P. S. Smith and others would have us believe that there is only one correct way to extract a senile cataract. It is but fair...