15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

An Investigation of the Application of Dynamic Sinusoidal Models to Statistical Parametric Speech Synthesis

Qiong Hu (1), Yannis Stylianou (2), Ranniery Maia (2), Korin Richmond (1), Junichi Yamagishi (1), Javier Latorre (2)

(1) University of Edinburgh, UK
(2) Toshiba Research Europe, UK

This paper applies a dynamic sinusoidal synthesis model to statistical parametric speech synthesis (HTS). For this, we utilise regularised cepstral coefficients to represent both the static amplitude and dynamic slope of selected sinusoids for statistical modelling. During synthesis, a dynamic sinusoidal model is used to reconstruct speech. A preference test is conducted to compare the selection of different sinusoids for cepstral representation. Our results show that when integrated with HTS, a relatively small number of sinusoids selected according to a perceptual criterion can produce quality comparable to using all harmonics. A Mean Opinion Score (MOS) test shows that our proposed statistical system is preferred to one using mel-cepstra from pitch synchronous spectral analysis.

Full Paper

Bibliographic reference.  Hu, Qiong / Stylianou, Yannis / Maia, Ranniery / Richmond, Korin / Yamagishi, Junichi / Latorre, Javier (2014): "An investigation of the application of dynamic sinusoidal models to statistical parametric speech synthesis", In INTERSPEECH-2014, 780-784.