Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

Implement the paper: https://arxiv.org/abs/1907.05321

This repository accompanies the paper "Learning Concept Embeddings from Temporal Data" (Meyer, Van Der Merwe, and Coetsee, 2018)

Time2Vec - Application to User Activity Data

Reproducing the paper: "Time2Vec: Learning a Vector Representation of Time" - https://arxiv.org/pdf/1907.05321.pdf

ECG Classification

Inter- and intra- patient ECG heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach

A flexible, intuitive and fast forecasting library

Unsupervised time series anomaly detection library

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

Keras Temporal Convolutional Network. Supports Python and R.

Reference implementation of real-time autoregressive wavenet inference

This is a TensorFlow implementation of the WaveNet generative neural network architecture https://deepmind.com/blog/wavenet-generative-model-raw-audio/ for image generation.

PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]

Wav2Vec for speech recognition, classification, and audio classification

SincNet is a neural architecture for efficiently processing raw audio samples.

Pytorch implementation of time-domain filterbanks

Filter Bank Implementaion as Convolutional Neural Network using Python Keras

LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a ve…

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

Zafar's Audio Functions in Python for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.

FinRL­®-Meta: Dynamic datasets and market environments for FinRL.

PyTorch implementation of the LEAF audio frontend

Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation

An implementation of WaveNet with fast generation

Transfer 🤗 Learning for Time Series Forecasting

1st Place solution to the Cornell Birdcall Identification competition.