World: a vocoder-based high-quality speech synthesis system for real-time applications
A vocoder-based speech synthesis system, named WORLD, was developed in an effort to
improve the sound quality of real-time applications using speech. Speech analysis …
improve the sound quality of real-time applications using speech. Speech analysis …
[HTML][HTML] D4C, a band-aperiodicity estimator for high-quality speech synthesis
M Morise - Speech Communication, 2016 - Elsevier
An algorithm is proposed for estimating the band aperiodicity of speech signals, where
“aperiodicity” is defined as the power ratio between the speech signal and the aperiodic …
“aperiodicity” is defined as the power ratio between the speech signal and the aperiodic …
[PDF][PDF] Harvest: A High-Performance Fundamental Frequency Estimator from Speech Signals.
M Morise - INTERSPEECH, 2017 - isca-archive.org
A fundamental frequency (F0) estimator named Harvest is described. The unique points of
Harvest are that it can obtain a reliable F0 contour and reduce the error that the voiced …
Harvest are that it can obtain a reliable F0 contour and reduce the error that the voiced …
A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis
S Takaki, J Yamagishi - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
In the state-of-the-art statistical parametric speech synthesis system, a speech analysis
module, eg STRAIGHT spectral analysis, is generally used for obtaining accurate and stable …
module, eg STRAIGHT spectral analysis, is generally used for obtaining accurate and stable …
Sound quality comparison among high-quality vocoders by using re-synthesized speech
M Morise, Y Watanabe - Acoustical Science and Technology, 2018 - jstage.jst.go.jp
Since we have released WORLD on GitHubà and have been continuously updating
WORLD to improve the sound quality of the synthesized speech, there is no information on …
WORLD to improve the sound quality of the synthesized speech, there is no information on …
[PDF][PDF] Low-Dimensional Representation of Spectral Envelope Without Deterioration for Full-Band Speech Analysis/Synthesis System.
A speech coding for a full-band speech analysis/synthesis system is described. In this work,
full-band speech is defined as speech with a sampling frequency above 40 kHz, whose …
full-band speech is defined as speech with a sampling frequency above 40 kHz, whose …
Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data
In this paper, we investigate the semi-supervised joint training of text to speech (TTS) and
automatic speech recognition (ASR), where a small amount of paired data and a large …
automatic speech recognition (ASR), where a small amount of paired data and a large …
Voice conversion with CycleRNN-based spectral mapping and finely tuned WaveNet vocoder
In this paper, we present a novel framework for a voice conversion (VC) system based on a
cyclic recurrent neural network (CycleRNN) and a finely tuned WaveNet vocoder. Even …
cyclic recurrent neural network (CycleRNN) and a finely tuned WaveNet vocoder. Even …
Efficient shallow wavenet vocoder using multiple samples output based on laplacian distribution and linear prediction
This paper presents a novel way for an efficient implementation scheme of shallow WaveNet
vocoder with multiple samples (segment) output based on the use of Laplacian distribution …
vocoder with multiple samples (segment) output based on the use of Laplacian distribution …
Human-in-the-loop speech-design system and its evaluation
D Kondo, M Morise - 2019 Asia-Pacific Signal and Information …, 2019 - ieeexplore.ieee.org
We propose human-in-the-loop (HITL) speech-design system with an interface. General text-
to-speech (TTS) systems generate the speech waveform from the input text without the need …
to-speech (TTS) systems generate the speech waveform from the input text without the need …