Model
FastSpeech
A neural network-based text-to-speech model that substantially improves speech naturalness compared with traditional concatenative and parametric synthesis methods.
Timeline (last 90 days)
Sep 23
End-to-end architectures such as Tacotron, FastSpeech, and VITS have compressed the overall text-to-audio latency from several seconds to hundreds of milliseconds.
Unverified50%