Statistical parametric speech synthesis

H Zen, K Tokuda, AW Black - speech communication, 2009 - Elsevier
This review gives a general overview of techniques used in statistical parametric speech
synthesis. One instance of these techniques, called hidden Markov model (HMM)-based …

Recent development of the HMM-based speech synthesis system (HTS)

H Zen, K Oura, T Nose, J Yamagishi, S Sako, T Toda… - 2009 - naist.repo.nii.ac.jp
Recent development of the HMM-based speech synthesis system (HTS) Page 1 Recent
development of the HMM-based speech synthesis system (HTS) Heiga Zen,*11 Keiichiro …

HMM-based emotional speech synthesis using average emotion model

L Qin, ZH Ling, YJ Wu, BF Zhang, RH Wang - Chinese Spoken Language …, 2006 - Springer
This paper presents a technique for synthesizing emotional speech based on an emotion-
independent model which is called “average emotion” model. The average emotion model is …

Building HMM-TTS voices on diverse data

V Wan, J Latorre, K Yanagisawa… - IEEE Journal of …, 2013 - ieeexplore.ieee.org
The statistical models of hidden Markov model based text-to-speech (HMM-TTS) systems
are typically built using homogeneous data. It is possible to acquire data from many different …

Minumum generation error linear regression based model adaptation for HMM-based speech synthesis

L Qin, YJ Wu, ZH Ling, RH Wang… - 2008 IEEE International …, 2008 - ieeexplore.ieee.org
Due to the inconsistency between the maximum likelihood (ML) based training and the
synthesis application in HMM-based speech synthesis, a minimum generation error (MGE) …

[PDF][PDF] Pulse density representation of spectrum for statistical speech processing.

Y Shiga - INTERSPEECH, 2009 - isca-archive.org
This study investigates a new spectral representation that is suitable for statistical parametric
speech synthesis. Statistical speech processing involves spectral averaging in the training …

An improved minimum generation error based model adaptation for HMM-based speech synthesis

YJ Wu, L Qin - … 2009 10th Annual Conference of the …, 2010 - nitech.repo.nii.ac.jp
A minimum 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 …

Model adaptation for HMM-based speech synthesis under minimum generation error criterion

L Qin, YJ Wu, ZH Ling, RH Wang - 2008 Tenth IEEE …, 2008 - ieeexplore.ieee.org
In order to solve the issues related to the maximum likelihood (ML) based HMM training for
HMM-based speech synthesis, a minimum generation error (MGE) criterion had been …

[PDF][PDF] List of modifications made in HTS (for version 2.3)

HTK HTS - 2015 - hts.sp.nitech.ac.jp
In HTS, the HTK HMM definition (please see HTKBook [1] Chapter 7) has been modified to
support MSD [2], stream-level tying, and adaptation of multi-stream HMMs. This section …

[PDF][PDF] List of modifications made in HTS (for version 2.1. 1)

K Oura - 2010 - hts.sp.nitech.ac.jp
In HTS, the HTK HMM definition (please see HTKBook [1] Chapter 7) has been modified to
support MSD [2], stream-level tying, and adaptation of multi-stream HMMs. This section …