IIIT Hyderabad Publications |
|||||||||
|
LTS Using Decision Forest of Regression Trees and Neural NetworksAuthors: Tanuja Sarkar,Sachin Joshi,Sathish Chandra Pammi,Kishore Prahallad Conference: in Proceedings of Interspeech, Brisbane, Australia Date: 2009-01-29 Report no: IIIT/TR/2009/36 AbstractLetter-to-sound (LTS) rules play a vital role in building a speech synthesis system. In this paper, we apply various Machine Learning approaches like Classifcation and Regression Trees (CART), Decision Forest, forest of Artificial Neural Network (ANN) and Auto Associative Neural Networks (AANN) for LTS rules. We used these techniques mainly for Schwa deletion 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 discriminative 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 primary 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. Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |