8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A Robust Training Algorithm Based on Neighborhood Information

Wing-Hei Au, Man-Hung Siu

Hong Kong University of Science and Technology, Hong Kong

Robustness is an important issue in automatic speech recognition systems. When the testing conditions do not match the training condition or when there is insufficient training data, the performance of a system trained by maximum likelihood criterion may degrade significantly. Different robust algorithms were proposed especially for cases in which the mismatch condition is known or can be estimated from the test data. In many practical cases, however, the mismatch information may not be available. In this paper, we propose a robust training algorithm that does not make any assumption about the mismatch condition. Instead, it is based on a neighborhood concept that appropriately broaden the model distributions to increase the model robustness. The proposed algorithm is evaluated in the Aurora3 tasks which shows that the neighborhood approach can reduce the degradation in mismatch conditions.

Full Paper

Bibliographic reference.  Au, Wing-Hei / Siu, Man-Hung (2004): "A robust training algorithm based on neighborhood information", In INTERSPEECH-2004, 153-156.