Optimizing segment label boundaries for statistical speech synthesis

This paper introduces a new optimization technique for moving segment labels (phone and subphonetic) to optimize statistical parametric speech synthesis models. The choice of objective measures is investigated thoroughly and listening tests show the results to significantly improve the quality of the generated speech equivalent to increasing the database size by 3 fold.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Alan W. Black, John Kominek
• Keywords: ICASSP 2009, Objective Measures, Parametric Speech Synthesis, Segment Labels, Signal Processing