samsad35/source-filter-vae
[SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder
This tool helps researchers and voice engineers analyze and modify speech recordings by separating fundamental voice characteristics. You input audio files, and it allows you to precisely control aspects like pitch (f0) and vocal tract shape (formants f1, f2, f3) to generate new speech. It's designed for someone working on speech synthesis, voice transformation, or acoustic analysis.
No commits in the last 6 months.
Use this if you need to dissect speech into its core components (source and filter) and then manipulate those components to create new, modified speech.
Not ideal if you're looking for a simple, off-the-shelf voice changer for end-user applications or if you don't have a technical understanding of speech acoustics.
Stars
45
Forks
5
Language
Python
License
AGPL-3.0
Category
Last pushed
Apr 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/samsad35/source-filter-vae"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.