XCORE-VOICE

OVERVIEW

xcore-voice is built upon xcore.ai – the fast, flexible, economical crossover processor designed to enable voice and intelligent IoT applications.

This is a software-defined, low-power voice solution that addresses multiple markets. High performance DSP algorithms are used to extract human speech from noisy environments at distance, while simultaneously running AI payloads such as wake words and speech recognition. The audio front end incorporates far-field voice processing, on/off-line voice command recognition and turnkey example designs that enable product designers to deliver ‘across-the-room’ voice interfaces quickly and cost-effectively with optimal audio quality.

APPLICATIONS

FAR-FIELD VOICE CONTROL

OFFLINE VOICE PROCESSING

LOCAL COMMAND PROCESSING

CUSTOMISED WAKE WORD

LOW POWER VOICE OFFLOAD

INDUSTRIAL VOICE CONTROL

KEY FEATURES

Voice Processing components

  • Two PDM microphone interfaces
  • Digital signal processing pipeline
  • Full duplex, stereo, Acoustic Echo Cancellation (AEC)
  • Reference audio via I2S with automatic bulk delay insertion
  • Point noise suppression via interference canceller
  • Switchable stationary noise suppressor
  • Programmable Automatic Gain Control (AGC)
  • Flexible audio output routing and filtering
  • Independent audio paths for communications and Automatic Speech Recognition (ASR)
  • Standard API for Simple integration of 3rd part speech recognition engines

Device Interface components

  • Full speed USB2.0 compliant device supporting USB Audio Class (UAC) 2.0
  • Flexible peripheral interfaces
  • Programmable digital general-purpose inputs and outputs

Example Designs utilising above components

  • Far-Field Voice Local Command (FFD)
  • Far-Field Voice Assistance (FFVA)
  • Asynchronous Sample Rate Convertor (ASRC)

Firmware Management

  • Boot from QSPI Flash
  • Default firmware image for power-on operation
  • Option to boot from a local host processor via SPI
  • Device Firmware Update (DFU) via USB or other transport

Power Consumption

  • Typical power consumption 300-350mW
  • Low power modes down to 55mW (using DEMO VNR)

3rd Party Speech Recognition Engines

  • Includes Sensory’s Wake Word & Phrase Recognition Engine, enabling simple creation of custom wake-words and voice commands via the VoiceHub
  • Cyberon DSpotter – local voice trigger and command recognition

LET’S GET STARTED

Getting started on xcore-voice is easy – simply purchase the dev kit and download the software!
Click the button below and follow the instructions.

BUY

Scroll to Top