This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.
Explains vowel shifts in different parts of the USA and predicts their survival over time.
Linguistic Agents flagship product is an intelligent command engine that bridges Natural Language (e.g. English) and Computer Language, enabling machines to understand and act upon normative human language.