Tree-Based Approaches to Automatic Generation of Speech Synthesis Rules for Prosodic Parameters

Yoichi YAMASHITA  Manabu TANAKA  Yoshitake AMAKO  Yasuo NOMURA  Yoshikazu OHTA  Atsunori KITOH  Osamu KAKUSHO  Riichiro MIZOGUCHI  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E76-A   No.11   pp.1934-1941
Publication Date: 1993/11/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Speech Synthesis: Current Technologies and Thier Application)
speech synthesis,  decision tree,  automatic rule generation,  accent component,  long noun phrase,  

Full Text: PDF(774.9KB)>>
Buy this Article

This paper describes automatic generation of speech synthesis rules which predict a stress level for each bunsetsu in long noun phrases. The rules are inductively inferred from a lot of speech data by using two kinds of tree-based methods, the conventional decision tree and the SBR-tree methods. The rule sets automatically generated by two methods have almost the same performance and decrease the prediction error to about 14 Hz from 23 Hz of the accent component value. The rate of the correct reproduction of the change for adjacent bunsetsu pairs is also used as a measure for evaluating the generated rule sets and they correctly reproduce the change of about 80%. The effectiveness of the rule sets is verified through the listening test. And, with regard to the comprehensiveness of the generated rules, the rules by the SBR-tree methods are very compact and easy to human experts to interpret and matches the former studies.