SANTA CLARA, Calif., Nov. 17, 2020 -- STMicroelectronics (ST;NYSE: STM), a global semiconductor leader serving customers across the spectrum of electronics applications, and DSP Concepts today announced four new high-performance audio front ends (AFE) with AVS qualified integrated voice processing. Launched as TalkTo for ST, the designs cover Alexa Voice Service for AWS IoT, near-field for wearables, speakerphones, and point-of-sale kiosks. Through this partnership, DSP Concepts ensures products based on these designs can be used for Alexa Built-in products using simple microcontrollers (MCUs).
Powered by DSP Concepts, TalkTo for ST jump-starts the design of a wide range of devices based on the high-performing STM32* MCU family. The energy-efficient STM32 is the world's most successful in the 32-bit Arm® Cortex®-M MCU family and is ideal for low-cost, small, and simple connected devices requiring state-of-the-art features like far-field audio capture and natural-language understanding.
Combined with the DSP Concepts' suite of proprietary Machine Learning & Microphone Processing algorithms, the two-mic solutions feature dynamic beam steering alongside noise reduction and adaptive interference cancellers to interference with no reference signal required. TalkTo for ST allows OEMs to rapidly meet the growing demand for high performance voice in a wide variety of environments.
"AVS Integration for AWS IoT Core can revolutionize users' expectations of smart devices by enabling easier access to their powerful features and delivering more rewarding experiences," said Daniel Colonna, Marketing Director, Microcontroller Division, STMicroelectronics. "Our reference design, one of the first to be approved by AWS, leverages the inherent strengths of STM32 microcontrollers and the supporting ecosystem to enable cost-efficient products with unbeatable functionality, small size, and fast time to market."
"We are at the very beginning of the voice-enabled device revolution," said Chin Beckmann, co-founder and CEO of DSP Concepts. "From shopping kiosks to automobiles, voice has consistently struggled outside the home. Companies like ST and partnerships like ours will trigger the next massive shift: enabling the proliferation of high fidelity, low-cost solutions into environments in and out of the home, once considered too noisy for effective voice interaction."
ST's AVS Integration for AWS IoT Core reference design contains a compact 36mm x 65mm main board that combines a high-performance STM32H743 MCU and Wi-Fi module. Unlike other devices commonly used for Alexa products, STM32 MCUs integrate all necessary system features, including powerful audio front-end processing, local wake-word detection, communication interfaces, and memory in a single chip. This creates a small board with a simple layout for cost-effective deployment in customers' end products.
TalkTo delivers outstanding far-field voice detection, even in noisy environments and with closely spaced microphones. The partnership between ST and DSP Concepts also gives OEMs instant access to:
- Audio Weaver: graphical tool to customize & tune audio processing models with embedded engine for Cortex-M4 and M7
- Voice-UI Quick-start Bundle: need-to-know design guidelines and tools
- Amazon wake word & connectivity stack to connect and interact with AVS for AWS IoT Core
- Noise reduction, echo cancellation and advanced beam-forming signal processing for far-field audio detection
ST Voice is AVS 2.1 Certified for AWS IoT with mono & stereo AEC and Adaptive Interference Canceller™ for reliable 'barge-in' at 6+ meters. The extensible two-mic reference designs are wake-word and ecosystem agnostic, with integrated playback processing.
The AFE Designs for ST Voice and more technical details of its operation, are available on ST.com and through local ST sales offices.
About DSP Concepts
DSP Concepts is the creator of Audio Weaver: the audio platform powering over 40M of the world's best devices and is the leading supplier to top-tier brands in automotive and consumer products. DSP Concepts provides leading brands like Tesla, GoPro, and Porsche with a low-code / no-code solution to voice UI integration and introduced a new emerging standard for embedded audio processing. We provide the only comprehensive, end-to-end solution that addresses the current challenges across industries working to innovate through audio and voice. The company's headquarters is located in Santa Clara, California with additional offices in Boston, Stuttgart and Taiwan.
ST is a global semiconductor leader delivering intelligent and energy-efficient products and solutions that power the electronics at the heart of everyday life. ST's products are found everywhere today, and together with our customers, we are enabling smarter driving and smarter factories, cities and homes, along with the next generation of mobile and Internet of Things devices.
By getting more from technology to get more from life, ST stands for life.augmented.
In 2019, the Company's net revenues were $9.56 billion, serving more than 100,000 customers worldwide. Further information can be found at www.st.com.