Toshiba AI Technology Catalog

  • Media recognition

Work records by speech (figure/item input)

Increase efficiency through speech input of work results, combining speech recognition technologies that operate on edge terminals.

  • Recognizes “Item and figure,” such as “Voltage: 100 volts” or “Current: 2 amperes”, then inputs them to the system.
  • Also enables work instructions from the system side, and judgments on whether the input figures are normal.
  • Uses voice triggers that quickly detect specified speech keywords and grammar recognition that selects phrases suited to input speech from among tens of thousands of phrase candidates, both of which can operate on edge terminals.


  • Work records in manufacturing, maintenance, and inspection workplaces

Benchmarks, strengths, and track record

  • Outstanding combination of speech recognition technologies (voice trigger and grammar recognition) for edge terminals suited to applications
  • Scope of item names and figures to be input can be customized.


Contact the Toshiba Corporate Research & Development Center

Please include the title “Toshiba AI Technology Catalog: Work records by speech (figure/item input)” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.