Cyberon Speech Recognition Technology – Light Bulb


The purpose of a design journey is to show, in a demonstrative way, how to incorporate the technology into a design. The base designs are by definition very simple to highlight the new technology and how it can be incorporated easily. Distinct lines are drawn between the application and the technology so the reader can more generalize how to incorporate it in their own design. Introduction ... » read more

Renesas / Cyberon Speech Recognition


Traditional voice or speech recognition technology is based on a trained model with specific words or phrases. Natural language processing is word-order independent. This requires large computing power to run the real time data through a neural network. The Cyberon approach is different, allowing the algorithms to run on a small, general purpose MCU. Click here to read more. » read more

Keyword Transformer: A Self-Attention Model For Keyword Spotting


The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or recurrent encoders. We investigate a range of ways to adapt the Transformer architecture to keyword spotting and introduce the Keyword Transformer (KWT), a fully... » read more

Speech Applications Will Enable A New Category Of Edge AI Chips


Speech recognition has become an increasingly important feature in a wide range of devices. Wakewords such as Alexa or OK Google or Siri have now become a standard feature of wearables, smart-speakers, mobile phones, and even laptops. These devices have already shipped in millions of units and consumers are getting better at utilizing this feature. The wakeword recognition feature is slowly evo... » read more

New Ways To Optimize Machine Learning


As more designers employ machine learning (ML) in their systems, they’re moving from simply getting the application to work to optimizing the power and performance of their implementations. Some techniques are available today. Others will take time to percolate through the design flow and tools before they become readily available to mainstream designers. Any new technology follows a basic... » read more

Week in Review: IoT, Security, Auto


Internet of Things The drone episode last month at Gatwick Airport in the United Kingdom forced the cancellation or diversion of more than 1,000 flights over three days. While local police arrested a couple suspected of being behind the drone flights, they were quickly exonerated and released. Questions remain on how airports should respond to such episodes, which are bound to happen again and... » read more

Making Sure A Heterogeneous Design Will Work


An explosion of various types of processors and localized memories on a chip or in a package is making it much more difficult to verify and test these devices, and to sign off with confidence. In addition to timing and clock domain crossing issues, which are becoming much more difficult to deal with in complex chips, some of the new devices are including AI, machine learning or deep learning... » read more

The Power Of Speech


With the widespread use of voice-activated virtual assistants, such as Apple’s Siri, Amazon’s Alexa, Microsoft’s Cortana, and the Google Assistant, voice has become an everyday way to interact with electronics. We’re talking to our devices more than ever, using speech to initiate searches, issue commands, and even make purchases. There are a number of reasons why using your voice to ... » read more

The Week In Review: Design


Synopsys inked a deal to acquire Coverity, a San Francisco-based security startup that builds tools to test source code for defects and security risks, for $375 million. The purchase price is $350 million plus another $25 million in debt. The deal is expected to close in Synopsys’ fiscal Q2. The company announced its financial results for fiscal Q1 ended Jan. 31, as well. Revenue was $479.0 m... » read more