HMM-based speech synthesis with an acoustic glottal source model
Item Type:Conference Paper
Citation:Cabral, J.P., Renals, S., Richmond, K. & Yamagishi, J., HMM-based speech synthesis with an acoustic glottal source model, The First Young Researchers Workshop in Speech Technology, Dublin, Ireland, 25 April, 2009
Cabral_2009.pdf (PDF) 63.02Kb
A major cause of degradation of speech quality in HMMbased speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.
Other Titles:The First Young Researchers Workshop in Speech Technology
Type of material:Conference Paper
Availability:Full text available