A new language model is proposed to cope with the scarcity of training data. The proposed multi-class N-gram achieves an accurate word prediction capability and high reliability with a small number of model parameters by clustering words multi-dimensionally into classes, where the left and right context are independently treated. Each multiple class is assigned by a grouping process based on the left and right neighboring characteristics. Furthermore, by introducing frequent word successions to partially include higher order statistics, multi-class N-grams are extended to more efficient multi-class composite N-grams. In comparison to conventional word tri-grams, the multi-class composite N-grams achieved 9.5% lower perplexity and a 16% lower word error rate in a speech recognition experiment with a 40% smaller parameter size.
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Experimental and Cognitive Psychology
- Linguistics and Language