Hacker News new | ask | show | jobs
by walterbell 4007 days ago
We need AGPL algorithms and training datasets for voice recognition, plus user-programmable open-source firmware for on-device wake word recognition.

If we can end the false privacy-convenience tradeoff, then the technology can be applied for goals defined by users rather than select business interests.

Nuance's Dragon NaturallySpeaking is a mature proprietary product that runs locally on Windows. It has an SDK for custom integration, http://www.nuance.com/for-developers/dragon/client-sdk/index...