Slashdot Mirror

← Back to Stories (view on slashdot.org)

Hacked Amazon Echo Controls a Wheelchair (roboticstrends.com)

Posted by samzenpus on from the just-say-the-word dept.

An anonymous reader writes with a cool hack for making an electric wheelchair voice activated. Robotics Trends reports: "Amazon Echo, which is designed around your voice, answers to 'Alexa' and can tell you scores, read your book, play your music, or check your calendar. And if you have a smart home, Echo can control lights and other technology. Bob Paradiso, however, wondered if he 'could push Echo's utility a little further.' He certainly did. Paradiso turned an electric wheelchair into a voice-controlled wheelchair using Echo, a Raspberry Pi and Arduino Uno. Echo thinks it's turning lights on and off, but it's really controlling the wheelchair. Paradiso says, 'Alexa, turn on left 4' and the wheelchair spins. He then says, 'Alexa, turn on forward 4' and the wheelchair moves forward."

1 of 23 comments (clear)

  1. Re:Hacked? by Anonymous Coward · · Score: 2, Interesting

    Seriously. Proprietary software running locally could probably be made to do it.

    There's also some efforts to make free-software voice recognition software that deserve a mention:

    http://www.voxforge.org/

    "VoxForge was set up to collect transcribed speech for use with Free and Open Source Speech Recognition Engines (on Linux, Windows and Mac).

    We will make available all submitted audio files under the GPL license, and then 'compile' them into acoustic models for use with Open Source speech recognition engines such as CMU Sphinx, ISIP, Julius (github) and HTK (note: HTK has distribution restrictions).
    Why Do We Need Free GPL Speech Audio?

    Most acoustic models used by 'Open Source' speech recognition (or Speech-to-Text) engines are closed source. They do not give you access to the speech audio and transcriptions (i.e. the speech corpus) used to create the acoustic model.

    The reason for this is that Free and Open Source ('FOSS') projects are required to purchase large speech corpora with restrictive licensing. Although there are a few instances of small FOSS speech corpora that could be used to create acoustic models, the vast majority of corpora (especially large corpora best suited to building good acoustic models) must be purchased under restrictive licenses.

    How Can You Help?

    Record yourself reading some text and upload your recordings to VoxForge."