Title :
Optimizing segment label boundaries for statistical speech synthesis
Author :
Black, Alan W. ; Kominek, John
Author_Institution :
Language Technol., Inst., Carnegie Mellon Univ., Pittsburgh, PA
Abstract :
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.
Keywords :
speech synthesis; statistical analysis; segment label boundary optimization; statistical parametric speech synthesis; statistical speech synthesis; Distortion measurement; Filters; Hidden Markov models; High temperature superconductors; Labeling; Natural languages; SPICE; Size measurement; Spatial databases; Speech synthesis; Label Boundary Optimization; Parametric Speech Synthesis; Speech Synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4960451
