• Publications
  • Influence
Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter Trajectory
TLDR
We propose a spectral conversion method for voice conversion based on maximum-likelihood estimation of a spectral parameter trajectory. Expand
  • 868
  • 115
  • PDF
Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model
TLDR
We propose a statistical approach to both an articulatory-to-acoustic mapping and an acoustic- to-articulatory inversion mapping without using phonetic information. Expand
  • 229
  • 40
A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis
TLDR
This paper describes a novel parameter generation algorithm for an HMM-based speech synthesis technique that considers not only the HMM likelihood maximized in the conventional algorithm but also a likelihood for a global variance (GV) of the generated trajectory. Expand
  • 476
  • 30
  • PDF
Speech Synthesis Based on Hidden Markov Models
TLDR
This paper gives a general overview of hidden Markov model-based speech synthesis, which has recently been demonstrated to be very effective in synthesizing speech. Expand
  • 363
  • 27
  • PDF
Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005
TLDR
In January 2005, an open evaluation of corpus-based text-to-speech synthesis systems using common speech datasets, named Blizzard Challenge 2005, was conducted. Expand
  • 251
  • 19
  • PDF
Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T)
TLDR
Pseudo-code written in natural language can aid the comprehension of source code in unfamiliar programming languages. Expand
  • 145
  • 16
  • PDF
Speaker-Dependent WaveNet Vocoder
TLDR
We propose a speaker-dependent WaveNet vocoder, a method of synthesizing speech waveforms with WaveNet, by utilizing acoustic features from existing vocoder as auxiliary features of WaveNet. Expand
  • 198
  • 15
  • PDF
An investigation of multi-speaker training for wavenet vocoder
TLDR
We propose speaker-dependent WaveNet vocoder, which is trained with a single speaker's speech data, is capable of modeling temporal waveform structure, such as phase information, and makes it possible to generate more naturally sounding synthetic voices compared to conventional high-quality vocoder. Expand
  • 78
  • 10
An overview of nitech HMM-based speech synthesis system for blizzard challenge 2005
TLDR
In the present paper, hidden Markov model (HMM) based speech synthesis system developed in Nagoya Institute of Technology (Nitech-HTS) for a competition of text-to-speech synthesis systems using the same speech databases, named Blizzard Challenge 2005, is described. Expand
  • 112
  • 10
  • PDF
Recent development of the HMM-based speech synthesis system (HTS)
TLDR
A statistical parametric approach to speech synthesis based on hidden Markov models (HMMs) has grown in popularity over the last few years. Expand
  • 66
  • 10
  • PDF