Amazon announced yesterday their advancements on Varying Speaking Styles with Neural Text-to-Speech. In this episode I talk about synthesized speech before this, why it matters, and what the (not that far) future might look like. This is one of the topics on voice technology I'm most passionated about.
Hosted on Acast. See acast.com/privacy for more information.
Informationen
- Sendung
- Veröffentlicht20. November 2018 um 12:30 UTC
- Länge4 Min.
- Folge132
- BewertungUnbedenklich