LTS using decision forest of regression trees and neural networks
Tanuja Sarkar, Sachin Joshi, Sathish Pammi, Kishore Prahallad · 2008
Letter-to-sound (LTS) rules play a vital role in building a speech synthesis system. In this paper, we apply various Machine Learning approaches like Classication and Regression Trees (CART), Decision Forest, forest of Articial Neural Network (ANN) and Auto Associative Neural Networks (AANN) for LTS rules. We used these techniques mainly for Schwa dele-tion in Hindi. We empirically show that the LTS using Decision Forest and Forest of ANNs outperforms the previous CART and normal ANN approaches respectively, and the non discrimina-tive learning technique of AANN could not capture the LTS rules as efciently as discriminative techniques. We explore use of syllabic features, namely, syllabic structure, onset of the syllable, number of syllables and place of Schwa along with pri-mary contextual features. The results showed that use of these features leads to good performance. The Decision Forest and forest of ANNs approaches yielded phone accuracy of 92.86% and 93.18 % respectively using the newly incorporated features for Hindi LTS.