Amazon has announced the fourth-generation version of its main Echo smart speaker, bringing a new spherical design and better sound performance. But the biggest change is a new, on-device speech recognition module that will locally process your audio on the Echo itself, making your requests faster than ever before.
One of the biggest additions to the new Echo is what Amazon’s calling the AZ1 Neural Edge silicon module, which will process the audio of your voice requests using local machine learning speech recognition algorithms before sending the command to the cloud. The process promises to save hundreds of milliseconds in response time for your Echo.
Developing. Check out our live blog for more news from the Amazon…