Auto-Regressive Deep Neural Network • Not fully text to speech: needs TTS features [1] Oord, Aaron van den, et al. "Wavenet: A generative model for raw audio." 3
Auto-Regressive Deep Neural Network • Not fully text to speech: needs TTS features Speaker 1 Speaker 2 Music [1] Oord, Aaron van den, et al. "Wavenet: A generative model for raw audio." 3
• Worked with a machine learning framework? • Worked with Keras? • Worked with computation graph frameworks (tensorflow, theano, etc)? • Rough understanding of WaveNet? 6
• Accessible without machine learning experience. • Tips and tricks on working efficiently. • Leave out on details (but feel free to ask!) • Non-goal: an objective comparison between frameworks. 7
‘cat’ or ‘dog’ • Neural network consisting of layers of neurons that compute intermediate steps. • These layers have weights, which determine the outcome. • We ‘train’ these weights: show an input and adjust the weights towards target. 8
Run on GPU and other hardware • Solution: computational graph libary. • Keras uses Theano or Tensorflow, and provides common interface: import keras.backend as K • Example time: adding two numbers together. 9
quantization • Categorical Distribution as output • Conditional Wavenet for TTS [1] Oord, Aaron van den, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel recurrent neural networks." 13
PyCharm and working with remote GPU servers/Cluster 4. Having Keras in pycharm project with editable install. 5. Smart Experiment Management with IDSIA-Sacred 6. TDD with Keras 18 If we had more time: