#iot "Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose" https://thenextweb.com/artificial-intelligence/2018/01/11/ai-learns-how-to-fool-text-to-speech-thats-bad-news-for-voice-assistants/

“Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose” https://thenextweb.com/artificial-intelligence/2018/01/11/ai-learns-how-to-fool-text-to-speech-thats-bad-news-for-voice-assistants/


Source: known.networkeffects.ca

 

gpotter

 

Leave a Reply

Your email address will not be published. Required fields are marked *