SoundHound Launches Dynamic Interaction
SoundHound AI, a provider of voice artificial intelligence, has introduced Dynamic Interaction, a breakthrough in conversational AI that not only recognizes and understands speech, but also responds and acts in real-time.
Where other voice technology requires wake words and relies on turn-taking to process requests, Dynamic Interaction uses fragment parsing, which breaks speech down to partial-utterances and processes them in real time, and full-duplex audio-visual integration.
Dynamic Interaction does the following
- Instantly follows and captures fluent speech in real time;
- Completely ignores off-topic speech, only responding to domain-specific topics, like the items on a menu.
- Confirms requests via audio and visuals, giving reassurance that an order or request has been understood accurately;
- Allows users to change, adapt, and delete requests in real time;
- Makes proactive suggestions to usesr based on a real-time interpretation of their speech;
- Allows users to input information via voice and touch interface interchangeably and simultaneously;
- Responds with audio and visual output and decides when to speak to the user vs. simply updating the visual output.
SoundHound says this new technology has broad applicability to many industries. As its first test ground, Dynamic Interaction will offer restaurants support for voice ordering at drive-thrus, kiosks, and via smartphone, tablet, and desktop ordering platforms.
Dynamic Interaction "is incredibly user-friendly and precise. Consumers won't have to modify how they speak to the voice assistant to get a useful response. They can just speak as naturally as they would to a human. As an added bonus they'll also have the means to instantly know and edit registered requests," said Keyvan Mohajer, co-founder and CEO of SoundHound, in a ststement. "In our 17 year-history of developing cutting-edge voice AI, this is perhaps the most important technical leap forward. We believe, just like how Apple's multitouch technology leapfrogged touch interfaces in 2009, this is a significant disruption in human-computer interfaces."