Tone correctness improvement in speaker dependent HMM-based Thai speech synthesis
Speech Communication
An Improvement of HSMM-Based Speech Synthesis by Duration-Dependent State Transition Probabilities
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
Graph-based partial hypothesis fusion for pen-aided speech input
IEEE Transactions on Audio, Speech, and Language Processing - Special issue on multimodal processing in speech-based interactions
Integrating articulatory features into HMM-based parametric speech synthesis
IEEE Transactions on Audio, Speech, and Language Processing
Hyperbolic structure of fundamental frequency contour
Proceedings of the 3rd International Universal Communication Symposium
An Analysis of HMM-based prediction of articulatory movements
Speech Communication
HMM-based emotional speech synthesis using average emotion model
ISCSLP'06 Proceedings of the 5th international conference on Chinese Spoken Language Processing
Impacts of machine translation and speech synthesis on speech-to-speech translation
Speech Communication
Hi-index | 0.00 |
This paper discusses a hidden Markov model (HMM) based on multi-space probability distribution (MSD). The HMMs are widely-used statistical models to characterize the sequence of speech spectra and have successfully been applied to speech recognition systems. From these facts, it is considered that the HMM is useful for modeling pitch patterns of speech. However, we cannot apply the conventional discrete or continuous HMMs to pitch pattern modeling since the observation sequence of the pitch pattern is composed of one-dimensional continuous values and a discrete symbol which represents "unvoiced". MSD-HMM includes discrete HMMs and continuous mixture HMMs as special cases, and further can model the sequence of observation vectors with variable dimension including zero-dimensional observations, i.e., discrete symbols. As a result, MSD-HMMs can model pitch patterns without heuristic assumption. We derive a reestimation algorithm for the extended HMM and show that it can find a critical point of the likelihood function.