kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization
-
Updated
Nov 7, 2025 - Jupyter Notebook
kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization
Graduation's final project submitted to the teaching staff from the Eletronics and Computing Engineering bachelor's course from the Polytechnic School of the Federal University of Rio de Janeiro as one of the necessary requirements for obtaining the Electronics and Computing Engineer degree.
Modular framework for audio corpus analysis, feature-based matching, and granular synthesis
Real-time voice-chat ransom note: learns the words people say in voice chat, then speaks what you type by stitching their own clips together through a virtual microphone. Concatenative unit selection, not AI voice cloning: no GPU, no TTS model, ~200 MB. Linux + Windows.
Three browser instruments for records with a sealed second channel — granular, wave terrain, latent mosaicing. AGPL-3.0.
To associate your repository with the concatenative-synthesis topic, visit your repo's landing page and select "manage topics."