https://github.com/idiap/idiaptts
A Python-based modular toolbox for building Deep Neural Network models (using PyTorch) for statistical parametric speech synthesis
https://github.com/idiap/idiaptts
Last synced: 4 months ago
JSON representation
A Python-based modular toolbox for building Deep Neural Network models (using PyTorch) for statistical parametric speech synthesis
- Host: GitHub
- URL: https://github.com/idiap/idiaptts
- Owner: idiap
- License: other
- Created: 2019-02-07T15:50:55.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2021-12-31T12:16:09.000Z (over 4 years ago)
- Last Synced: 2025-03-23T01:02:08.647Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 40.7 MB
- Stars: 23
- Watchers: 8
- Forks: 8
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# IdiapTTS
This repository contains the Idiap Text-to-Speech system developed at the [Idiap Research Institute](https://www.idiap.ch/en), Martigny, Switzerland.
Contact:
It is an almost purely Python-based modular toolbox for building Deep Neural Network models (using [PyTorch](https://pytorch.org/)) for statistical parametric speech synthesis. It provides scripts for feature extraction and preparation which are based on third-party tools (e.g. [Festival](http://www.cstr.ed.ac.uk/projects/festival/)). It uses the [WORLD](https://github.com/mmorise/World) vocoder (i.e. its [Python wrapper](https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder)) for waveform generation. The framework was highly inspired by [Merlin](https://github.com/CSTR-Edinburgh/merlin) and reuses some of its data preparation functionalities. In contrast to Merlin it is intended to be more modular and allowing prototyping purely in Python.
It comes with recipes in the spirit of [Kaldi](https://github.com/kaldi-asr/kaldi) located in separate repositories.
IdiapTTS is distributed under the MIT license, allowing unrestricted commercial and non-commercial use.
IdiapTTS is tested with: **Python 3.6**
## Installation
Follow the instructions given in *INSTALL.md*.
## Experiments
Instructions to run specific experiments are in the *README* files of the respective *egs* repositories:
* https://github.com/idiap/idiaptts_egs_ljspeech */s1* contains TTS with a duration and acoustic model.
## Publications
#### Interspeech '18: A Neural Model to Predict Parameters for a Generalized Command Response Model of Intonation
Instructions to produce results similar to those reported in the paper can be found at https://github.com/idiap/idiaptts_egs_blizzard08_roger *s1/*.
#### Icassp'19: An End-to-End Network to Synthesize Intonation using a Generalized Command Response Model
Instructions to reproduce the results of the paper can be found in https://github.com/idiap/idiaptts_egs_blizzard08_roger *s2/*.
#### SSW'10: Neural VTLN for Speaker Adaptation in TTS
Instructions to produce results similar to those in the paper can be found at https://github.com/idiap/idiaptts_egs_vctk *s1/*.