- Grand Piano Keys with ArduinoPosted 3 days ago
- Wireless Power TransferPosted 4 days ago
- Robot Punchers with ArduinoPosted 5 days ago
- A minimal 3D-printed scalePosted 7 days ago
- Expanding the pins of a microcontrollerPosted 1 week ago
- Let’s create a small level with a matrix displayPosted 2 weeks ago
- ChatGPT: Writing Code with Artificial IntelligencePosted 2 weeks ago
- Free Webinar: Arduino IoT Cloud and ESP32 DemoboardPosted 2 weeks ago
- Maker Faire Rome – The European edition and FAE Technology launch the contest “MY Maker PCBA: your electronics for a better planet”Posted 3 months ago
- Efficient and Compact Stereo Power Amplifier: Unleash High-Quality Audio with the PAM8610Posted 4 months ago
ReSpeaker 4-Mic Array: Voice Detection and Directional Capabilities for Raspberry Pi
There are an increasing number of software solutions available for adding voice agent technology to the Raspberry Pi, including Alexa agent (Amazon Echo) or the Google Assist technology. Yet, typical microphone add-on boards are often not up to the task of accurate voice detection especially in multi-speaker environments.
Seeed Studios has a solution in the form of a $24.90 ReSpeaker 4-Mic Array for Raspberry Pi.
The Respeaker 4-Mic Array is equipped with a quad-channel AC108 ADC from Chinese firm X-Powers. The AC108 features a 108 dB dynamic range at ADC rates between 8kHz and 24kHz, and offers integrated I2S/TDM output transition circuitry for high definition voice capture.
The Respeaker 4-Mic Array’s four analog mics support voice recognition at up to three meters. The 65 x 65 x 9mm, 20-gram device does not handle voice output, but you can use the Pi’s headphone jack for output. A pair of Seeed Grove interfaces is also onboard.
The add-on board also provides an LED ring made up of 12x APA102 LEDs that can light up to indicate the location of the voice the agent is conversing with.
Main Features:
- Raspberry Pi compatible(Support Raspberry Pi Zero and Zero W, Raspberry Pi B+, Raspberry Pi 2 B and Raspberry Pi 3 B)
- 4 Microphones
- 3 meters radius voice capture
- 2 Grove Interfaces
- 12 APA102 User LEDs
- Software Algorithm: VAD(Voice Activity Detection), DOA(Direction of Arrival) and KWS(Keyword Search)