8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Discriminative Combination of Multiple Linear Predictions for Speech Recognition

Zhijian Ou, Wang Zuoying

Tsinghua University, China

In this paper, new analyses are provided for the problems of applying linear prediction (LP) HMMs in speech recognition. It is shown that, apart from simply aggregating all predictors in one LP, which produces inconsistent results, 'combination' provides another useful way to implement complex dependencies. A method by discriminative combination of multiple LPs (DCoLP) is proposed, with a component-LP selection heuristic. The resulting DCoLP model was tested on a speaker-independent, large vocabulary continuous speech recognition task, and showed improved performance over the standard HMM with comparable computation cost.

Full Paper

Bibliographic reference.  Ou, Zhijian / Zuoying, Wang (2004): "Discriminative combination of multiple linear predictions for speech recognition", In INTERSPEECH-2004, 553-556.