We Continue the Work of Those
Who Were the First.

  • Electrotechnics
  • Electrical Engineering
  • Light & Lighting
  • Power Engineering
  • Transportation
  • Automation
  • Communication
  • Smart Buildings
  • Industry
  • Innovation

Current issue

ELEKTRO 3/2019 was released on March 11th 2019. Its digital version will be available on March 11th 2019.

Topic: Amper 2019 – 271 International trade fair for electrical engineering

Main Article
Smart Cities (part 8)

SVĚTLO (Light) 2/2019 was released on March 15th 2019. Its digital version will be available immediately.

Architectural and scenic lighting
The architectural lighting of Bečov nad Teplou castle
Lighting design in a nutshell – Part 41
The analyse of light picture a little more theoretic

Day light
Biggest mistakes in day lighting design of buildings

Machine-learning system tackles speech and object recognition, all at once

18.09.2018 | MIT | www.mit.edu

MIT computer scientists have developed a system that learns to identify objects within an image, based on a spoken description of the image. Given an image and an audio caption, the model will highlight in real-time the relevant regions of the image being described.

Unlike current speech-recognition technologies, the model doesn’t require manual transcriptions and annotations of the examples it’s trained on. Instead, it learns words directly from recorded speech clips and objects in raw images, and associates them with one another.

Machine learning system

The model can currently recognize only several hundred different words and object types. But the researchers hope that one day their combined speech-object recognition technique could save countless hours of manual labor and open new doors in speech and image recognition.

Read more at MIT

Image Credit: Christine Daniloff

-jk-