miniDSP Introduces UMA-8 USB Microphone Array for Voice-Activated Applications

May 18 2017, 03:10
The new miniDSP UMA-8 is a high-performance yet low cost multichannel USB microphone array built around XMOS multicore technology, designed for voice-recognition application development. Seven high-performance MEMS microphones are configured in a circular arrangement to provide high-quality voice capture for a wide range of applications. Leveraging the onboard DSP processing, the UMA-8 supports voice algorithms including beamforming, noise reduction, acoustic echo cancellation and de-reverb. 

Developed with applications in voice-activated control, smart assistants, robotics, conferencing, and more in mind, the UMA-8 pocket-size platform targets both DIYers and the OEM market, and was engineered for flexibility in firmware, software and hardware. All the resources are available for application development, including precompiled firmware versions, expansion connectors providing connectivity for additional PDM microphones, I2S in/out expansion and GPIO. According to miniDSP, this will allow even non-technical users to enjoy a plug&play experience, while advanced users can fine-tune all DSP parameters with a realtime Win/Mac GUI for optimum performance. 

For advanced users, full control and configuration of the DSP array processing parameters are available with a real-time GUI. This can be used to fine-tune the various algorithms: acoustic echo cancellation, noise reduction, voice activation detect, and so on, dramatically improving voice pickup. The UMA-8 board is a fully compliant UAC2 audio interface with driverless support for Mac/Linux and ASIO drivers for Windows. With its USB API for direction of arrival, 8ch raw audio mode via USB Audio, PDM to I2S conversion, the new miniDSP board offers the level of flexibility demanded by developers.

The UMA-8 is now available at USD $95 per unit on miniDSP’s webshop. Step by step application notes are available for setup and configuration of the UMA-8 with the most common smart assistants currently available, including Amazon Alexa Voice + Raspberry Pi, Microsoft Cortana, and Apple Siri. miniDSP will be expanding those application notes in the future.
related items