Submission + - Google's DeepMind developed a new speech synthesis AI algorithm called WaveNet
Artem Tashkinov writes: To this date the researches behind Google's DeepMind company have been creating the AI algorithms which could hardly be applied in real life aside from pure entertainment purposes, the Go game being the most recent example, however their most recent development, a speech synthesis AI algorithm called WaveNet beats the two existing methods of generating human speech by a long shot — at least 50% by Google's own estimates. The only problem with this new approach is that it's very computationally expensive. The results are even more impressive considering the fact that WaveNet allows to mimic breathing, mouth movements, intonation and other features of human's speech, and it can be easily trained to generate any voice using a very small sample database.