8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Rapid EM Training based on Model-Integration

Shinichi Yoshizawa (1), Kiyohiro Shikano (2)

(1) Matsushita Electric Industrial Co.,LTd., Japan
(2) Nara Institute of Science and Technology, Japan

Recently, speech recognition technique has started being used in various products. In order to make a good acoustic model, usually a lot of training speech data is needed. However, due to the right of voice and privacy issues, it is not easy to collect a lot of training data. Statistical models which have been trained and transformed from speech data do not have the above mentioned problem, and are comparatively easy to obtain. Therefore, a training technique which can make an acoustic model by using statistical models as training data is preferred. This paper describes a new method called Rapid EM Training based on Model-Integration and shows that the proposed method is evaluated positively.

Full Paper

Bibliographic reference.  Yoshizawa, Shinichi / Shikano, Kiyohiro (2004): "Rapid EM training based on model-integration", In INTERSPEECH-2004, 649-652.