Self-organized language modeling for speech recognition
Readings in speech recognition
Poor estimates of context are worse than none
HLT '90 Proceedings of the workshop on Speech and Natural Language
Fundamentals of speech recognition
Fundamentals of speech recognition
Class-based n-gram models of natural language
Computational Linguistics
Structural ambiguity and lexical relations
Computational Linguistics - Special issue on using large corpora: I
Word association and MI-Trigger-based language modeling
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Is the contextual information relevant in text clustering by compression?
Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
Ngram models are simple in language modeling and have been successfully used in speech recognition and other tasks. However, they can only capture the short distance context dependency within an n-words window where currently the largest practical n for a natural language is three while much of the context dependency in a natural language occurs beyond a three words window. In order to incorporate this kind of long distance context dependency in the ngram model of our Mandarin speech recognition system, this paper proposes a novel MI-Ngram modeling approach. This new MI-Ngram model consists of two components: a normal ngram model and a novel MI model. The ngram model captures the short distance context dependency within an n-words window while the MI model captures the context dependency between the word pairs over a long distance by using the concept of mutual information. That is, the MI-Ngram model incorporates the word occurrences beyond the scope of the normal ngram model. It is found that MI-Ngram modeling has much better performance than the normal word ngram modeling. Experimentation shows that about 20% of errors can be corrected by using a MI-Trigram model compared with the pure word trigram model.