VocalFusion mono-AEC voice processor

XMOS high-performance digital signal processing solutions help you build a voice interface quickly into your products. Our mono-AEC voice processor gives you up-close voice capture and processing accuracy at far-field range – even in noisy environments.

We offer two development kits: our our linear array is ideal if you want to integrate a voice interface into kitchen appliances and smart-panels, including smart lighting, heating and security solutions. Our circular array has a 360 degree voice capture field – ideal if you’re developing ‘centre of room’ products, such as a table-top smart speaker.

Distance

Accurate voice capture and barge-in from across the room, even when music is playing loudly and the commands are spoken softly.

Clarity

Mono-acoustic echo cancellation, noise suppression and dereverberation cut unwanted noise and echo for optimised ASR processing.

Direction

Wake-word engine detects voice commands and beamforming tracks the speaker of interest. You get best in class performance at all angles and over long distances.

Our rich optimisation parameters for the XVF3100 voice processor lets you adjust for noise attenuation, gain control and residual echo so you can tailor the best voice capture performance for your product. And our engineers are on hand to help you move rapidly from prototype to tuning, and from testing to volume production with a world-class product.

Development Kit – linear array

XK-VF3100-L33

  • VocalFusion 4-mic mono-AEC development kit – linear array

    XVF3100 processor board

    • Micro-USB connector for power (optional USB2.0 device connectivity)
    • Low jitter, audio quality clock
    • DAC with integrated headphone amplifier
    • 4 configurable user input buttons
    • 13 user-controlled LEDs
    • xTAG interface for JTAG debug

    XVF3100 voice processor (programmable for far-field voice capture)

    • Wake-word engine by Sensory
    • Full duplex Acoustic Echo Cancellation (AEC)
    • Barge-in
    • 4-microphone adaptive beamformer
    • Dereverberation
    • Noise suppression
    • Automatic Gain Control (AGC)
    • Direction of arrival (DOA) indication

    Microphone Array

    • Linear, 100mm long
    • 4 x Infineon IM69D130 PDM (Pulse Density Modulation) MEMS microphones
    • 33mm inter-mic spacing

    Connectivity

    • Inter-Integrated Sound (I2S) audio interfaces
    • Inter-Integrated Circuit (I2C) serial control interface
    • High speed USB2.0 compliant
    • Multi-channel USB audio class 1.0
    • 128-pin TQFP package 0.4 pitch

    To get started with the development kit, you’ll also need:

    • Laptop or PC with some stereo music content and 2 free USB ports
    • Internet connection
    • Powered loudspeaker

Development Kit – circular array

XK-VF3100-C43

  • VocalFusion 4-mic mono-AEC circular development kit – circular array.

    XVF3100 processor board

    • Micro-USB connector for power (optional USB2.0 device connectivity)
    • Low jitter, audio quality clock
    • DAC with integrated headphone amplifier
    • 4 configurable user input buttons
    • 13 user-controlled LEDs
    • xTAG interface for JTAG debug

    XVF3100 voice processor (programmable for far-field voice capture)

    • Wake-word engine by Sensory
    • Full duplex Acoustic Echo Cancellation (AEC)
    • Barge-in
    • 4-microphone adaptive beamformer
    • Dereverberation
    • Noise suppression
    • Automatic Gain Control (AGC)
    • Direction of arrival (DOA) indication

    Microphone array

    • Circular, 90mm diameter
    • 4 x Infineon IM69D130 PDM (Pulse Density Modulation) MEMS microphones
    • 43mm radius microphone spacing

    Connectivity

    • Inter-Integrated Sound (I2S) audio interfaces
    • Inter-Integrated Circuit (I2C) serial control interface
    • High speed USB2.0 compliant
    • Multi-channel USB audio class 1.0
    • 128-pin TQFP package 0.4 pitch

Silicon

XK-VF3100-TQ128-C

  • XVF3100 voice processor (programmable for far-field voice capture)

    • Wake-word engine by Sensory
    • Full duplex Acoustic Echo Cancellation (AEC)
    • Barge-in
    • 4-microphone adaptive beamformer
    • Dereverberation
    • Noise suppression
    • Automatic Gain Control (AGC)
    • Direction of arrival (DOA) indication