@inproceedings{b48a1ad562c740febda5b4ecbd1a4cfe,
title = "Tree-based unit selection for English speech synthesis",
abstract = "In concatenative speech synthesis for English, scarcity of speech data for many contexts is a serious problem. In this paper, we propose a new unit selection scheme using a decision-tree-based clustering method that combines acoustic and linguistic knowledge with statistical modeling. This approach not only allows us to find a trainable and consistent set of generalized allophonic models but also to achieve some local optimality with respect to the limited training data. To evaluate the validity of this algorithm, regression tree generation has been carried out for both vowels and consonants from 200 phonetically balanced sentences read by a female speaker. Experimental results show that regression trees offer a promising solution for the data scarcity problem.",
author = "Wang, {Wern Jun} and Campbell, {W. N.} and Naoto Iwahashi and Yoshinori Sagisaka",
year = "1993",
month = jan,
day = "1",
language = "English",
isbn = "0780309464",
series = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
publisher = "Publ by IEEE",
pages = "II--191--II--194",
booktitle = "Speech Processing",
note = "1993 IEEE International Conference on Acoustics, Speech and Signal Processing ; Conference date: 27-04-1993 Through 30-04-1993",
}