State Duration Modeling for HMM-Based Speech Synthesis
IEICE Transactions on Information and Systems2007Vol. E90-D(3), pp. 692–693
Citations Over TimeTop 12% of 2007 papers
Abstract
This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the state duration PDF and demonstrate improvements in the duration of synthesized speech.
Related Papers
- → Language Model Pre-training Method in Machine Translation Based on Named Entity Recognition(2020)14 cited
- → Improving Arabic HMM based speech synthesis quality(2006)30 cited
- → TechWare: HMM-based speech synthesis resources [Best of the Web](2009)4 cited
- → Implementation of speech synthesis based on HMM using PADAS database(2015)3 cited
- → HMM-based Vietnamese speech synthesis(2015)1 cited