A State Duration Generation Algorithm Considering Global Variance for HMM-based Speech Synthesis
نویسندگان
چکیده
The speech parameter generation algorithm considering global variance (GV) for HMM-based speech synthesis proved to be effective against the over-smoothing problem. In this paper this idea is extended to the generation of state duration. A GV model on syllable duration is proposed and a state duration generation algorithm considering this GV model is presented in details. By improving the GV likelihood on syllable duration, the over-averaging effect on generated state duration is much alleviated. Experimental results are promising which show that the proposed method outperforms the conventional one and the naturalness of synthetic speech is improved.
منابع مشابه
Overview of NIT HMM - based speech synthesis system for Blizzard Challenge 2009
We describe a hidden Markov model (HMM)-based speech synthesis system developed at the Nagoya Institute of Technology (NIT) for Blizzard Challenge 2009. We incorporated several state-of-the-art technologies into this system, including the Speech Transformation and Representation using Adaptive Interpolation of weiGHTed spectrum (STRAIGHT) vocoder, minimum generation error (MGE) training, phone ...
متن کاملOverview of NIT HMM - based speech synthesis system for Blizzard Challenge 2010
This paper describes a hidden Markov model (HMM)-based speech synthesis system developed for the Blizzard Challenge 2010. This system employs STRAIGHT vocoding, minimum generation error (MGE) training, minimum generation error linear regression (MGELR) based model adaptation, the Bayesian speech synthesis framework, and the parameter generation algorithm considering global variance. The real-ti...
متن کاملSpeech parameter generation algorithm considering global variance for HMM-based speech synthesis
This paper describes a novel parameter generation algorithm for the HMM-based speech synthesis. The conventional algorithm generates a trajectory of static features that maximizes an output probability of a parameter sequence consisting of the static and dynamic features from HMMs under an actual constraint between the two features. The generated trajectory is often excessively smoothed due to ...
متن کاملA speech parameter generation algorithm using local variance for HMM-based speech synthesis
This paper proposes a parameter generation algorithm using local variance (LV) constraint of spectral parameter trajectory for HMM-based speech synthesis. In the parameter generation process, we take account of both the HMM likelihood of speech feature vectors and a likelihood for LVs. To model LV precisely, we use dynamic features of LV with context-dependent HMMs. The objective experimental r...
متن کاملImproved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV
For constructing a speech synthesis system which can achieve diverse voices, we have been developing a speaker independent approach of HMM-based speech synthesis in which statistical average voice models are adapted to a target speaker using a small amount of speech data. In this paper, we incorporate a high-quality speech vocoding method STRAIGHT and a parameter generation algorithm with globa...
متن کامل