ReSpeaker Core v2.0

By Seeed Technology Co., Ltd. 128

ReSpeaker Core v2.0

Seeed Technology's ReSpeaker Core v2.0 allows developers to create powerful and impactful voice and sound interfaces. Suitable both as a base for smart assistance as well as responding to environmental sounds, it was designed with the idea that developers deserve to have many options available.

The high-performance platform ReSpeaker Core v2.0, powered by the Axol Core module featuring the Rockchip RK3229 Quad-Core Arm® Cortex®-A7 with a Mali 400 MP GPU, 1 GB of DDR3 RAM, and a PMU, which runs the Debian OS. These features provide developers with much more flexibility and more resources to create projects.

A Kingston 4 GB eMMC which enables the OS to run onboard; a WiFi/BLE module; USB, Grove, and HDMI connectors; the onboard 6-microphone array; LED ring; and more peripherals are located around the core.

The ReSpeaker includes an onboard 6-mic array with professional voice enhancement algorithms with Axol Core, a software-based approach to voice enhancement. It allows the ReSpeaker to process the audio received through the six far-field microphones in real-time. The ReSpeaker supports noise suppression (NS), keyword wake-up, direction of arrival (DoA), beamforming (BF), and acoustic echo cancellation (AEC). Seeed's BF and AEC algorithms are provided by Alango, a professional audio DSP company used in the automotive industry.

While projects have different requirements and goals, the quad-core solution allows users to run numerous software solutions such as algorithms, NLP services, smart assistants, operating systems, and more. Customers who have suggestions regarding services that they would like Seeed to support officially can suggest them on Seeed's forums, or submit a merge request to Seeed's GitHub.

Audio output is available via the 3.5 mm audio jack (output only), as well as a JST two-pin connector and Bluetooth. The ReSpeaker Core v2.0 supports video output through HDMI*, enabling developers to create rich visual interfaces to pair with a voice interface. The graphics processing unit (GPU) is not fully implemented on Debian; 1080p video playback will be available July 2018; Android 8.1 will support 4k video on release.

Features Applications
  • Debian-based Linux system
  • SDK for speech algorithms with full documents
  • C++ SDK and Python wrapper
  • Speech algorithms and features:
    • Keyword spotting (wake-up)
    • BF
    • DoA
    • NS
    • AEC and automatic gain control (AGC)
  • All-in-one solution with high-performance SoC
  • 8-channel ADC for 6 microphone array and 2 loopbacks (hardware loopback)
  • Smart speaker
  • Intelligent voice assistant system
  • Voice recorder
  • Voice conferencing system
  • Meeting communication equipment
  • Voice interacting robot
  • Car voice assistant
  • Other scenarios utilizing voice interfaces

New Products:

102990883

Categories

Top