A generation error function considering dynamic properties of speech parameters for minimum generation error training for hidden Markov model-based speech synthesis
نویسندگان
چکیده
منابع مشابه
Local minimum generation error criterion for hybrid HMM speech synthesis
This paper presents an HMM-driven hybrid speech synthesis approach in which unit selection concatenative synthesis is used to improve the quality of the statistical system using a Local Minimum Generation Error (LMGE) during the synthesis stage. The idea behind this approach is to combine the robustness due to HMMs with the naturalness of concatenated units. Unlike the conventional hybrid appro...
متن کاملMinimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis
A minimum generation error (MGE) criterion had been proposed to solve the issues related to maximum likelihood (ML) based HMM training in HMM-based speech synthesis. In this paper, we improve the MGE criterion by imposing a log spectral distortion (LSD) instead of the Euclidean distance to define the generation error between the original and generated line spectral pair (LSP) coefficients. More...
متن کاملAn improved minimum generation error based model adaptation for HMM-based speech synthesis
Aminimum generation error (MGE) criterion had been proposed for model training in HMM-based speech synthesis. In this paper, we apply the MGE criterion to model adaptation for HMM-based speech synthesis, and introduce an MGE linear regression (MGELR) based model adaptation algorithm, where the regression matrices used to transform source models are optimized so as to minimize the generation err...
متن کاملTowards minimum perceptual error training for DNN-based speech synthesis
We propose to use a perceptually-oriented domain to improve the quality of text-to-speech generated by deep neural networks (DNNs). We train a DNN that predicts the parameters required for speech reconstruction but whose cost function is calculated in another domain. In this paper, to represent this perceptual domain we extract an approximated version of the SpectroTemporal Excitation Pattern t...
متن کاملCross-Validation and Minimum Generation Error based Decision Tree Pruning for HMM-based Speech Synthesis
This paper presents a decision tree pruning method for the model clustering of HMM-based parametric speech synthesis by cross-validation (CV) under the minimum generation error (MGE) criterion. Decision-tree-based model clustering is an important component in the training process of an HMM based speech synthesis system. Conventionally, the maximum likelihood (ML) criterion is employed to choose...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Acoustical Science and Technology
سال: 2013
ISSN: 1346-3969,1347-5177
DOI: 10.1250/ast.34.123