Dreamtonics / turksfeat
Resources for "Simple Speech Representation Learning from Perceptual Data".
☆11Updated last year
Alternatives and similar repositories for turksfeat:
Users that are interested in turksfeat are comparing it to the libraries listed below
- Noise generators for vocoder☆19Updated 6 years ago
- Zero-data (yet trainable) probabilistic fundamental frequency estimator.☆18Updated 6 years ago
- Python wrapper for Sinsy☆51Updated last year
- Hed and supporting files for Chinese NNSVS Dataset Creation☆13Updated 2 years ago
- Very fast and efficient large multi-instrumental music transformer with 8k sequence length, dynamic MIDI notes encoding, full MIDI instru…☆11Updated last year
- WaveNet implementation using tf.estimator☆21Updated last year
- An implementation of "Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction", in ISMIR 2023☆22Updated last year
- ☆10Updated 5 years ago
- ☆22Updated 4 months ago
- Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals☆16Updated 8 months ago
- ☆15Updated 2 years ago
- Algorithms to automatically recognize guitar effects and retrieve their parameters for timbre reproduction☆23Updated 2 years ago
- Code accompanying ML4MD ICML 2020 paper - "Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance".☆29Updated 4 years ago
- ☆17Updated 3 years ago
- This is the accompanying repository to the paper - Automatic Estimation of Singing Voice Musical Dynamics☆13Updated 5 months ago
- Sound examples for the Neural Parametric Singing Synthesizer (NPSS)☆22Updated 3 years ago
- A minimum inference engine for DiffSinger☆34Updated last year
- FVN is now obsolete. Please use CAPRICEP instead. I will stop updating this tool. Frequency domain variants of Velvet Noise, a flexible b…☆37Updated 4 years ago
- 22人で童謡を5曲ずつ歌ってつくった歌唱データベースです。☆13Updated 2 years ago
- Code for "A diffusion-inspired training strategy for singing voice extraction in the waveform domain" (ISMIR 2022)☆16Updated 2 years ago
- ☆11Updated 2 months ago
- ☆16Updated last year
- The official implementation of DMEL the method presented in the paper "DMEL: The differentiable log-Mel spectrogram as a trainable layer …☆19Updated 3 months ago
- Generating drum loops using the Wave-U-Net conditioned on intuitive parameters.☆23Updated 4 years ago
- This branch of Asteroid contains code for the vocal harmony and chamber ensemble separation related papers.☆11Updated 5 months ago
- Code for the paper: Unified Gradient Reweighting for Model Biasing with Applications to Source Separation☆14Updated 4 years ago
- Music Demixing Challenge Submission Repo☆15Updated last year
- Repo of my master thesis at Pompeu Fabra University: "Towards album artwork generation based on audio". We analyze VAEs and GANs to condi…☆11Updated 3 years ago
- A transformer neural network that generates symbolic music improvising on chord changes☆19Updated 9 months ago
- Supplementary Materials of ISMIR 2022 paper "Analysis and detection of singing techniques in repertoires of J-POP solo singers" by Yuya Y…☆21Updated 11 months ago