The new NXP far-field offline voice control solution is based on the i.MX RT106L crossover microcontroller (MCU), which addresses the market demand for embedded voice control in a broad range of smart home, commercial and industrial markets.
The availability of NXP’s i.MX RT106L MCU-based voice control solution makes it possible for original equipment manufacturers (OEMs) to now leverage a complete production ready solution to drastically reduce system cost and time to market. The solution delivers private, secure, low latency, hands-free experiences to end users.
Additionally, the local voice control solution eliminates the costs and complexities of cloud connectivity and can help protect user’s privacy by enabling audio to be processed directly on the device. This is achieved with integrated, machine-learning-based, automatic speech recognition (ASR) technology, delivered in partnership with Sonos, which recently acquired Snips, a pioneer company in embedded voice recognition software for businesses, products and services.
“The collaboration with NXP to launch an industry-leading solution based on Voice Commands by Sonos provides a new level of flexibility and speed for OEMs seeking to quickly develop and bring to market advanced offline voice control solutions that offer end-users completely seamless experiences at home and at work while eliminating any privacy concerns,” says Joseph Dureau, VP Voice Experience at Sonos.
The i.MX RT106L is an edge-ready solution-specific member of the i.MX RT1060 family of crossover MCUs targeting offline embedded local voice control applications. It features NXP’s advanced implementation of the Arm Cortex-M7 core, which operates at speeds up to 600 MHz. The i.MX RT106L processor is licensed to run NXP’s turnkey local voice control software solution, which includes the Voice Commands by Sonos technology, a machine learning far field audio front end, acoustic echo cancellation, barge-in, ambient noise reduction, beamforming, playback processing and many additional features.
In addition to delivering the voice control capability, the i.MX RT106L MCU can also be used as the main microcontroller in most IoT product implementations. The SLN-LOCAL-IOT development kit is available now, priced at an MSRP of $149 USD.
NXP i.MX RT600 Family
NXP Semiconductors also announced market availability of the i.MX RT600 crossover microcontroller (MCU) family, an ideal solution for ultra-low power, secure edge applications including audio, voice and machine learning. Machine learning support is optimized using a Glow neural network compiler.
The new MCU family features an Arm Cortex-M33 processor running up to 300 MHz, optional Cadence Tensilica HiFi 4 audio/voice digital signal processor (DSP) running up to 600 MHz with Quad 32x32 MAC, and up to 4.5 MB on-chip SRAM with zero wait-state access for critical code and data. The 28nm FD-SOI process solution us optimized for both active and leakage power and features NXP’s advanced embedded security technology - EdgeLock 400A.
The i.MX RT series of crossover MCUs are designed to bridge the gap between high-performance and integration while minimizing costs to meet today's need for high performance embedded processing at the edge. The series delivers advanced microcontrollers (MCUs) with the functionality of applications processors, at low costs, enabling advanced computation and machine learning capabilities in millions of connected edge devices.
The i.MX RT600 MCU family is available with a suggested resale price starting at $4.50 (USD) for 10,000-unit quantities. An i.MX RT600 evaluation kit (pictured above) is available at a suggested resale price of $129 (USD). i.MX RT600 is fully supported by the NXP MCUXpresso suite of tools and software, including IDE support, system configuration and extensive driver and middleware support. In addition, Cadence's Xplorer IDE for i.MX RT600, DSP function libraries and audio codecs are offered complementary.
NXP also partnered with Alango Technologies, DSP Concepts and Sensory to provide high performance voice pre-processing and recognition software, plus professional audio libraries and tools. Furthermore, the integrated HiFi 4 DSP will be supported with the NXP eIQ for Glow machine learning compiler, accessible in the next MCUXpresso SDK release planned for Q2 2020.