I'm currently interested in doing a project based on wavenet, but I haven't found any implementation, that even resembles something like Google Deepmind advertises here. The most popular implementation links to this example output which isn't even remotely close Deepminds examples of randomly generated speech.
Topic machine-learning
Category Data Science
Here is an issue in the github about Speech Generation that might answer your question: https://github.com/ibab/tensorflow-wavenet/issues/47
They manage to generate random speech, for example:
https://soundcloud.com/user-952268654/wavenet-28k-steps-of-100k-samples
https://soundcloud.com/user-731806733/generated-larger-1
Otherwise, I didn't found any code that directly generate random speech, but an implementation in Keras seems to be easier to use:
Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.