How to Achieve High-Accuracy Keyword Spotting on Cortex-M Processors
January 24, 2018
It IS possible to optimize neural network architectures to fit within the memory and compute constraints of microcontrollers – without sacrificing accuracy. We explain how, and explore the potential of depthwise separable convolutional neural networks for implementing keyword spotting on Cortex-M processors.
Keyword spotting (KWS) is a critical component for enabling speech-based user interactions on smart devices. It requires real-time response and high accuracy to ensure a good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech-processing algorithms.
To read the full article, click here
Related Semiconductor IP
- Real-time Pixel Processor for Vision applications
- 64-bit RISC-V core with in-order single issue pipeline. Tiny Linux-capable processor for IoT applications.
- Tiny, Ultra-Low-Power Embedded RISC-V Processor
- Low-Power Embedded RISC-V Processor
- Enhanced-Processing Embedded RISC-V Processor
Related Blogs
- Enhanced ARM DesignStart eliminates upfront license fees for ARM Cortex-M0 and Cortex-M3 processors
- What will it take for FPGAs to become as ubiquitous as processors?
- How many people does it take to design an SoC? - Redux. Building brains with processors.
- Microprocessor Report publishes extremely interesting comparison of STMicroelectronics SPEAr-1300 and Xilinx Zynq ARM-based, dual core application processors
Latest Blogs
- AI in Design Verification: Where It Works and Where It Doesn’t
- PCIe 7.0 fundamentals: Baseline ordering rules
- Ensuring reliability in Advanced IC design
- A Closer Look at proteanTecs Health and Performance Management Solutions Portfolio
- Enabling Memory Choice for Modern AI Systems: Tenstorrent and Rambus Deliver Flexible, Power-Efficient Solutions