STiLL - Speech Technology in Language Learning May 25-27, 1998 Marholmen, Sweden

WebGrader(TM): A Multilingual Pronunciation Practice Tool

Leonardo Neumeyer, Horacio Franco, Victor Abrash, Luc Julia, Orith Ronen, Harry Bratt, Jehan Bing, Vassilis Digalakis, Marikka Rypa

Speech Technology and Research Laboratory, SRI International, Menlo Park, USA

WebGrader(TM) is a pronunciation grading tool designed for practicing pronunciation in a second language. The system uses SRI's speech recognition [1] and pronunciation scoring [2][3][4] technologies. The application client was implemented by using the Java platform to facilitate deployment and updates of software and content over the World Wide Web. We present the overall system architecture, user-interface design, scoring algorithms, and a preliminary user study.

References

1. V. Digalakis and H. Murveit, "Genones: Optimizing the Degree of Mixture Tying in a Large Vocabulary Hidden Markov Model Based Speech Recognizer," IEEE Trans. Speech Audio Processing, pp. 281-289, July 1996.
2. J. Bernstein, M.Cohen, H. Murveit, D. Rtischev, and M. Weintraub, "Automatic Evaluation and Training in English Pronunciation," Proceedings ICSLP, 1990.
3. L. Neumeyer, H. Franco, M. Weintraub, and P. Price, "Automatic Text-Independent Pronunciation Scoring of Foreign Language Student Speech," Proceedings ICSLP, 1996.
4. H. Franco, L. Neumeyer, Y. Kim, and O. Ronen, "Automatic Pronunciation Scoring for Language Instruction," Proceedings ICASSP, 1997.

Full Paper

Bibliographic reference.  Neumeyer, Leonardo / Franco, Horacio / Abrash, Victor / Julia, Luc / Ronen, Orith / Bratt, Harry / Bing, Jehan / Digalakis, Vassilis / Rypa, Marikka (1998): "Webgrader(TM): a multilingual pronunciation practice tool", In STiLL-1998, 61-64.