Babble-rnn: Generating speech from speech with LSTM networks

There is plenty of interest in recurrent neural networks (RNNs) for the generation of data that is meaningful, and even fascinating to humans. Popular examples generate everything from credible (but fabricated) passages from Shakespeare, incredible (but highly likely) fake-news clickbait, to completely simulated handwritten sentences that shadow the style of the original writer. Such compelling examples demonstrate the power of recurrent neural networks for modelling human generated data, and recreating completely new data from those models. They can be understood by anybody, humanising the world of "AI". Inspired, Consected, sponsored research into the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations.