philayres / babble-rnn
babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations. The idea is to learn to speak through imitation, much like a baby might.
☆35Updated 6 years ago
Related projects: ⓘ
- Programs with word vectors, RNN, NLP stuff, etc☆18Updated 7 years ago
- Learns to classify names by country of origin with a LSTM RNN in Torch☆9Updated 7 years ago
- ☆12Updated this week
- This is the code used in the paper "Diagonal RNNs in Symbolic Music Modeling"☆17Updated 7 years ago
- An implementation of zoneout regularizer on LSTM-RNN by Tensorflow☆25Updated 7 years ago
- RNN Approaches to Integer Sequence Learning--the famous Kaggle competition☆27Updated 7 years ago
- Generate images of neural network achitectures.☆18Updated 7 years ago
- ☆66Updated 8 years ago
- This ist the repository for the term project Speech Recognition using Deep Neural Networks for the course ELEC-E5510-Speech Recognition☆12Updated 8 years ago
- ☆21Updated 8 years ago
- Portal of Johannes and Felix's RNN implementation and further modifications for ASR☆21Updated 9 years ago
- A super simple way to do distributed hyperparameter tuning with Keras and Mongo☆30Updated 7 years ago
- Backpropagation-through-time library for TensorFlow☆28Updated 6 years ago
- This is the code for the 'Tensorflow Neural Network' Live session by @Sirajology on Youtube☆31Updated 5 years ago
- Code for my blog post "Design by Evolution"☆21Updated 6 years ago
- A brief experiment in making a convolutional auto-encoder with TensorFlow.☆15Updated 8 years ago
- Audio Analysis by Conceptor☆30Updated 9 years ago
- minimal implementation of style transfer☆10Updated 7 years ago
- WaveNet for unconditional speech generation - Theano Implementation