jakezhaojb / Deep-Music-Autoencoder
The repo involves a Deep Learning method, Stacked Denoising Autoencoder. The repo exploits "paracel", which is a new parallel computing framework
☆50Updated 8 years ago
Related projects: ⓘ
- Recurrent Neural Network language modeling toolkit☆39Updated 10 years ago
- Deep Manifold Learning on Music Audio☆36Updated 8 years ago
- Build a deep autoencoder. Acoustically monitor the influence of the middle code layer using a Kork nanoKontroller2.☆64Updated 8 years ago
- ☆66Updated 8 years ago
- CURRENNT -- CUDA-enabled machine learning library for recurrent neural network☆16Updated 4 years ago
- MSc AI Project on generative deep networks and neural style transfer for audio☆64Updated 7 years ago
- Implementation of WaveNet: A Generative Model for Raw Audio☆67Updated 8 years ago
- ☆19Updated 9 years ago
- Deep Convolutional Networks on the Pitch Spiral for Musical Instrument Recognition☆42Updated 8 years ago
- ☆37Updated 9 years ago
- Generative Adversial Network for music composition☆43Updated 7 years ago
- MXNet implementation of WaveNet☆20Updated 7 years ago
- Do STFT in Keras☆63Updated 7 years ago
- ☆22Updated 5 years ago
- Audio captioning RNN model in Keras☆15Updated 8 years ago
- Deep Recurrent Neural Networks☆30Updated 8 years ago
- Language Modeling with Sum-Product Networks☆20Updated 10 years ago
- Auralisation of learned features in CNN (for audio)☆42Updated 7 years ago
- tools around preparing TIMIT for HMM (with HTK) and deep learning (with Theano) methods☆78Updated 9 years ago
- WaveNet for unconditional speech generation - Theano Implementation☆32Updated 7 years ago
- This is the code used in the paper "Diagonal RNNs in Symbolic Music Modeling"☆17Updated 7 years ago
- Bunch of scripts for working with Kaldi.☆9Updated 6 years ago
- ☆52Updated 6 years ago
- Theano implementation of CTC. Applied on TIMIT and a Toy dataset.☆34Updated 8 years ago
- An implementation of zoneout regularizer on LSTM-RNN by Tensorflow☆25Updated 7 years ago
- CTC implementation in Theano.☆42Updated 8 years ago
- Visually informed embedding of word (VIEW) is a tool for transferring multimodal background knowledge to NLP algorithms.☆30Updated 8 years ago
- LSTM Python library using Cython☆38Updated 9 years ago
- code referenced in "Towards universal neural nets: Gibbs machines and ACE", Galin Georgiev, http://arxiv.org/abs/1508.06585☆14Updated 9 years ago
- Quick and Dirty TensorFlow command framework to train and evaluate models and make inference☆56Updated 5 years ago