YCY

pytorch-NMF. A pytorch package for non-negative matrix factorization.

music-spectrogram-diffusion-pytorch. Python

spectrogram-inversion. spectrogram inversion tools in PyTorch. Documentation: https://spectrogram-inversion.readthedocs.io

kamui. Python

pytorch_FFTNet. A pytorch implementation of FFTNet.

constant-memory-waveglow. PyTorch implementation of NVIDIA WaveGlow with constant memory cost.

music-demixing-challenge-ismir-2021-entry. The training code for the 4th place model at MDX 2021 leaderboard A.

variational-diffwave. Python

philtorch. Fast linear discrete time filtering in PyTorch.

phase-unwrapping. try out different PU algorithms.

wavenet-like-vocoder. Basic wavenet and fftnet vocoder model.

torch-fftconv. Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

kazane. Simple sinc interpolation in PyTorch.

danna-sep. Python

eva. A screaming vocal samples dataset.

hrtf-notebooks. Some HRTF experiments I made.

torchlru. Python

bela-hrir-convolver. Jupyter Notebook

ar-diffwave. Python

norbert. Painless Wiener filters for audio separation

pytorch-wise-ale. Jupyter Notebook

bayesian-pitch-tracking-python. statistical pitch tracking

translation-invariant. A pytorch implementation of translation-invariant network using in music transcription.

deepsphere-pytorch-geometric. DeepSphere: a graph-based spherical CNN (PyTorch)

audiotensor. Python

DL_HW2. Python

IIAP_dtw. multicomponent dtw.

ape-examples. C++

presentations. My presentation materials in the past.

4a2a. Jupyter Notebook

building-nn-with-numpy. numpy lenet implementation.

MIR_HW2. Python

MIR_HW1. Jupyter Notebook

pytorch-wav-datasets. Python

ML_HW3. My implementation of homework 3 for the Machine Learning class in NCTU (course number 5088).

SignalAndSystem_Special_Topic. just write this to convert the csv files i get to txt, so that i can plot them in gnuplot.

guitar-plucking-estimation. Python

vae-audio. Variational auto-encoders for audio

yoyolicoris.

DL_HW3. Python

omnizart. Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

audio-diffusion-pytorch. Audio generation using diffusion models, in PyTorch.

rho-gmvae-synth. Reproducing code for Learning Disentangled Representations of Timbre and Pitch for Musical Instrument Sounds Using Gaussian Mixture Variational Autoencoders

multi-layered-cepstrum. A recursive Fourier transform (FT) structure that suppresses convolutional noise.

sdx-submissions. Sound Demixing Challenge Submission Repo

ML_HW1. My implementation of homework 1 for the Machine Learning class in NCTU (course number 5088).