XCORE-VOICE

Example Designs

XCORE-VOICE is a highly flexible voice solution that allows you to pick and choose voice components to run alongside your desired AI model. Detailed documentation is available to guide you through options as highlighted in the sections below.

We have included several example designs that will enable you to get started immediately.
Following that you can download the source code to further compile, according to your needs.

XK-VOICE-L71

click to expand

Far-Field Voice Local Command

  • Dual PDM microphone with point and stationary noise reduction with integrated speech recognition engine.
  • Recognising 16 sample commands with control of peripherals via UART.​ Optional audio play-back “spoken response”.
  • Easily modified, provided as source with extensive libraries.  Create your own custom through our partners.

BLOCK DIAGRAM

click to expand

DOCUMENTATION

XK-VOICE-L71

click to expand

Far-Field Voice Assistant

  • 2-microphone far-field voice assistant front-end
  • Audio pipeline including echo cancelation, interference cancelling and noise suppression
  • Stereo reference input and voice assistant output each supported as I2S or USB (UAC2.0)

BLOCK DIAGRAM

click to expand

DOCUMENTATION

XK-VOICE-L71

click to expand

Asynchronous Sample Rate Convertor (ASRC)

  • I2S to USB interface supporting asynchronous sampling rates between 44.1 kHz – 192 kHz
  • Bidirectional signal path

BLOCK DIAGRAM

click to expand

DOCUMENTATION

Developer Resources

An XMOS solution is a convenient way to access a collection of software, examples, libraries and documentation for developers with an application in mind, and where all the components are guaranteed to work together.

XTC Tools

XCORE-VOICE SDK

DOCUMENTATIONSOFTWARE
QUICK START GUIDE (HTML) (PDF)
PROGRAMMING GUIDE​ (HTML) (PDF)
BUILD SYSTEM GUIDE (HTML)
DOWNLOAD THE XCORE-VOICE SDK

Frameworks

XMOS Frameworks are a collection of high-level components, already interoperable and sharing a common design approach.​

FRAMEWORKDESCRIPTIONDOCUMENTATION

FWK-VOICE

A collection of audio and voice signal processing components, implemented to use the 32-bit Block-Floating Point arithmetic of the xcore.ai Vector Processing Unit (VPU)​HTML​​
CONTAINED WITHIN FWK-VOICEDESCRIPTIONDOCUMENTATION
Acoustic Echo Canceller (AEC)​​Configurable for number of microphones and play-back channels​HTML​​
Automatic Delay Estimation and Correction (ADEC)​Functions for measuring and correcting delay offsets between  AEC reference and loudspeaker signals​HTML​​
Interference Canceller (IC)​Point noise cancellation, using two microphone input​HTML
Noise Suppression (NS)​Removes stationary noise​HTML
Automatic Gain Control (AGC)​Maintains output between target levels​HTML
Voice To Noise Ratio Estimator (VNR)​ML based alternative to a classic VAD, providing a more informative estimation of voice presence in noise.​HTML
Asynchronous Sample Rate Convertor (ASRC)Provides asynchronous signal exchange between two interfacesHTML
FRAMEWORKDESCRIPTIONDOCUMENTATION

FWK-IO

IO PeripheralsHTML

FWK-RTOS

XMOS’s SMP port of FreeRTOS​HTML
SMP DEMO

Libraries

XMOS Libraries provide reusable software, as source, for common functions​

LIBRARYDESCRIPTIONDOCUMENTATION

LIB_MIC_ARRAY

Allows 1 to 16 PDM microphones to be connected to an xcore device, with configurable filtering and decimation.​HTML​​

LIB_XCORE_MATH

Comprehensive library of mathematical and DSP functions, including integer, float, vectorised and complex operations.​HTML​​

Speech Recognition Partners

PRE-BUILT EXAMPLE

This is for evaluation purposes only. Please refer to the following quick start guide

Buy