Methods for Applying Dynamic Sinusoidal Models to Statistical Parametric Speech Synthesis

Qiong Hu, Yannis Stylianou, Ranniery Maia, Korin Richmond, Junichi Yamagishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Sinusoidal vocoders can generate high quality speech, but they have not been extensively applied to statistical parametric speech synthesis. This paper presents two ways for using dynamic sinusoidal models for statistical speech synthesis, enabling the sinusoid parameters to be modelled in HMM-based synthesis. In the first method, features extracted from a fixed- and low-dimensional, perception-based dynamic sinusoidal model (PDM) are statistically modelled directly. In the second method, we convert both static amplitude and dynamic slope from all the harmonics of a signal, which we term the Harmonic Dynamic Model (HDM), to intermediate parameters (regularised cepstral coefficients) for modelling. During synthesis, HDM is then used to reconstruct speech. We have compared the voice quality of these two methods to the STRAIGHT cepstrum-based vocoder with mixed excitation in formal listening tests. Our results show that HDM with intermediate parameters can generate comparable quality as STRAIGHT, while PDM direct modelling seems promising in terms of producing good speech quality without resorting to intermediate parameters such as cepstra.
Original languageEnglish
Title of host publicationAcoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
Publication statusPublished - 2015


Dive into the research topics of 'Methods for Applying Dynamic Sinusoidal Models to Statistical Parametric Speech Synthesis'. Together they form a unique fingerprint.

Cite this