Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A high-quality speech analysis, manipulation and synthesis system
| Date | Stars |
|---|---|
| 2026-07-24 | 1332 |
| 2026-07-25 | 1332 |
| 2026-07-28 | 1332 |
| 2026-07-30 | 1332 |
| 2026-08-06 | 1332 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# WORLD - a high-quality speech analysis, manipulation and synthesis system WORLD is free software for high-quality speech analysis, manipulation and synthesis. It can estimate Fundamental frequency (F0), aperiodicity and spectral envelope and also generate the speech like input speech with only estimated parameters. This source code is released under the modified-BSD license. There is no patent in all algorithms in WORLD. ## Introduction of WORLD family (2025/02/21) I introduce useful software in WORLD. If you want to introduce your project in WORLD, please contact me. PyWorldVocoder (https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder) is a Python wrapper for World Vocoder. Python-WORLD (https://github.com/tuanad121/Python-WORLD) is line-by-line implementation of WORLD vocoder (Matlab, C++) in python. world-class (https://github.com/yukara-ikemiya/world-class) is a C++ library of WORLD. World.JS (https://github.com/GloomyGhost-MosquitoSeal/World.JS) is a JavaScript Wrapper for World Vocoder. World.NET (https://github.com/aqtq314/World.NET) is a C# Wrapper for World Vocoder. WorldInApple (https://github.com/fuziki/WorldInApple) is a Swift wrapper for World Vocoder. DotnetWorld (https://github.com/yamachu/DotnetWorld) is a C# wrapper for WORLD. JA-WORLD (https://gitlab.com/f-matano44/world-for-java) is an independent Java port of WORLD vocoder. The Speech Signal Processing Toolkit ([SPTK](https://github.com/sp-nitech/SPTK)) wraps WORLD as UNIX-like commands. - DIO and Harvest -> `pitch` - https://sp-nitech.github.io/sptk/4.3/main/pitch.html - D4C -> `ap` - https://sp-nitech.github.io/sptk/4.3/main/ap.html - CheapTrick -> `pitch_spec` - https://sp-nitech.github.io/sptk/4.3/main/pitch_spec.html - Synthesis -> `world_synth` - https://sp-nitech.github.io/sptk/4.3/main/world_synth.html [diffsptk](https://github.com/sp-nitech/diffsptk) implements some of the WORLD components within the PyTorch framework. - D4C -> `Aperiodicity` - https://sp-nitech.github.io/diffsptk/2.5.0/modules/ap.html - CheapTrick -> `PitchAdaptiveSpectralAnalysis` - https://sp-nitech.github.io/diffsptk/2.5.0/modules/pitch_spec.html Note: To avoid making the project complicated, I decided not to merge it to my repository and introduce your project here. The other reason is that I can't support some computer languages. ## References When you cite the latest version of WORLD in your paper, please use the sentence "WORLD \[1\] (D4C edition [2])" and cite the following papers. [1] M. Morise, F. Yokomori, and K. Ozawa: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications, IEICE transactions on information and systems, vol. E99-D, no. 7, pp. 1877-1884, 2016. https://www.jstage.jst.go.jp/article/transinf/E99.D/7/E99.D_2015EDP7457/_article [2] M. Morise: D4C, a band-aperiodicity estimator for high-quality speech synthesis, Speech Communication, vol. 84, pp. 57-65, Nov. 2016. http://www.sciencedirect.com/science/article/pii/S0167639316300413 If you used the real-time synthesis function, you can refer the following reference. [3] M. Morise: Implementation of sequential real-time waveform generator for high-quality vocoder, in Proc. APSIPA ASC 2020, pp. 821-825, Online, Dec. 7-10, 2020. http://www.apsipa.org/proceedings/2020/pdfs/0000821.pdf In CheapTrick, you can refer the following references. [4] M. Morise: CheapTrick, a spectral envelope estimator for high-quality speech synthesis, Speech Communication, vol. 67, pp. 1-7, March 2015. http://www.sciencedirect.com/science/article/pii/S0167639314000697 [5] M. Morise: Error evaluation of an F0-adaptive spectral envelope estimator in robustness against the additive noise and F0 error, IEICE transactions on information and systems, vol. E98-D, no. 7, pp. 1405-1408, July 2015. In DIO, you can refer the following reference. [6] M. Morise, H. Kawahara and H. Katayose: Fast and reliable F0 estimation method based on the period extraction
Excerpt of 5,255 characters
Read on GitHub
146
Giulio Paci
79
8
8
Aby Louw · South Africa
4
Kanru Hua
4
Ryuichi Yamamoto · @line · Japan
4
3
Katsuya Iida · Japan
2
Yusuke Yamada · Japan
2
2
2
1
Sébastien Le Maguer · University of Helsinki · Finland
1
1
1
1
Shiyin Kang
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:477fef73266ec140, topic:speech-synthesis, readme:speech synthesis