5th International Conference on Spoken Language Processing
Proper noun pronunciation generation is a particularly challenging problem in speech recognition since a large percentage of proper nouns often defy typical letter-to-sound conversion rules. In this paper, we present decision tree methods which outperform neural network techniques. Using the decision tree method, we have achieved an overall error rate of 45.5%, which is a 35% reduction over the previous techniques. Our best system is a binary decision tree that uses a context length of 3 and employs information gain ratio as the splitting rule.
Bibliographic reference. Ngan, Julie / Ganapathiraju, Aravind / Picone, Joseph (1998): "Improved surname pronunciations using decision trees", In ICSLP-1998, paper 0384.