Voice-Capture Devices Grace IoT and Consumer Designs | Sensors Magazine
XMOS will demonstrate its comprehensive portfolio of VocalFusion true-stereo, voice-capture solutions for far-field voice-enabled stereo smart TVs, soundbars, and set-top boxes at Computex 2018 in June. The technology captures voice commands for use in Alexa, Google, DuerOS, and other voice-enabled artificial intelligence (AI) and internet of things (IoT) systems. The company will also be previewing next-gen VocalSorcery blind-source separation technology.
VocalFusion voice processors deliver voice digital signal processing (DSP) including a full duplex acoustic echo canceller (AEC) with barge-in capability that enables users to interrupt or pause a device that’s playing music, and an adaptive beamformer that follows a speaker. Additional dereverberation, automatic gain control, and noise suppression provide clear voice interaction experiences even in noisy environments. The processor interfaces directly to four PDM microphones in a linear array with 33.33-mm inter-mic spacing, making it viable for integration into flat screens and products found at the edge of a room.
VocalSorcery is a blind sound source signal separation technology that spatially identifies individual speakers or conversations within a crowded noisy audio environment to optimize voice capture and input into speech recognition systems. This technology solves the cocktail-party problem, and opens a wide variety of applications from video and conference calls, to automotive.