XMOS VocalFusion® voice processors capture voice interactions and commands from across the room. These high-performance devices are designed for use in conference calling devices (human-to-human), or devices which connect with automatic speech recognition systems (human-to-machine) systems, either on the cloud or local application processor. This document applies to all far-field human to machine (ASR) use cases.
This document aims to help engineers and developers in the planning of tests during development. VocalFusion can be deployed in a diverse range of applications and this document provides general guidelines, recommendations, and areas to consider when developing, testing and optimising the deployment of VocalFusion in devices with ASR connectivity.
