PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
-
Updated
Aug 3, 2021 - Python
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis
[SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder
A Java audio-playback class, modeled on javax.sound.sampled.Clip, enhanced with concurrent playback and dynamic handling of volume, pan and frequency. Maven version.
A more powerful, intuitive, and concurrency safe Clip, for Java audio needs.
Examples demonstrating the use of AudioCue
implement ptich control model of the paper of Javier Fernandez "Wide Open Spaces: A statistical technique for measuring space creation in professional soccer" by jaeminiman
Browser-based emulation of the Technics SL-1200 MK2 pitch section with real-time playback-rate control, accurate RPM calculation, Tap Tempo, and client-side WAV export. Built with React, TypeScript, Vite, and the Web Audio API.
Browser-based vinyl pitch engine with true Technics SL-1200 MK2 behaviour. Pitch, RPM, BPM, Tap Tempo, no timestretch.
Examples of the use of AudioCue (Maven version)
Guides, phonetic tools, and speaking exercises to achieve clear and natural German pronunciation.
Vanillia Javascript Client-side application enabling to upload an MP3 file, change it's pitch, play the newer version and export it, if good enough, to a WAV file format.
Add a description, image, and links to the pitch-control topic page so that developers can more easily learn about it.
To associate your repository with the pitch-control topic, visit your repo's landing page and select "manage topics."