Voice Control RaspberyPi Smart AR Glasses

A smart ar glasses base on Raspberry and cloud service

Public Chat
Similar projects worth following
Ar glasses is a very interesting topic. There are products such as Google glasses and Microsoft Hololens. I see many people share their achievements. I also want to make my own smart AR glasses. Because I am Chinese, I use a lot of Chinese resources and services. You can also use resources and services suitable for you. First of all, I would like to thank all geeks who share their designs and achievements. Their achievements have inspired me.

First of all, I think my project is useful and interesting. So I first made a list of scenarios and set a priority based on my abilities. First, I used it to show the abilities of AR glasses and to identify the modules needed for the project. Current functions include: Current Time Query, Line Query (By Bus), animal and plant identification, qrcode recognition, and installing new functions based on qrcode.


The project is divided into hardware part and software part. At present, in order to highlight the characteristics of AR glasses, only voice control is supported. 


The hardware part is mainly controlled by raspberry pi. Input and output of voice control by using USB sound card. Use the camera to capture pictures and display them with LCD screen and atomic mirror to ensure that the photos we take are what we need.In the future, from a practical point of view, a rocker or even a Bluetooth keyboard may be added. In fact, I have included a Bluetooth keyboard / mouse in my project, but I can't make good use of them. As the basic spectacle frame, I chose the head mounted magnifying glass as the foundation, which temporarily meets the current needs and is very easy to make. This also simplifies the current hardware selection. In the future, I hope to make it light enough to make it more like a pair of glasses. If you can have a better design, I hope you can share it.


The software part mainly uses cloud services, including offline wake-up, instruction recognition and a simple l process engine based on data bus.


Read more »

  • 1 × RaspberryPi Zero Main control
  • 1 × RaspberyPi 400(optional) Development environment main control
  • 1 × USB sound card Capacitors / Ceramic
  • 1 × LCD 2.0inch Capacitors / Ceramic
  • 1 × RaspberyPi Camera

View all 10 components

View all 4 project logs

  • 1
    Setup off-line speech recognition

    Now there are fewer and fewer open source speech recognition modules, and the test results are not ideal. The latest one that can be found is vosk, but vosk does not support raspberry pie 0. Finally, I chose Speechrecogonition + pocketsphinx as the solution for offline speech recognition. In order to ensure the recognition success rate, after several rounds of tests, I chose "my good friend" as the wake-up word, and made a special recognition file. You can also choose your favorite wake-up words. The only suggestion is to consider the recognition success rate.

    现在开源语音识别模块越来越少,而且经过测试效果并不理想。能够找到的最新的是VOSK,但是VOSK不支持树莓派0。最终我选择 Speechrecogonition + pocketsphinx作为离线语音识别的解决方案。为了确保识别成功率,经过多轮测试,我选择“My Good Friend”作为唤醒词,并且制作了专门的识别文件。你也可以选择你喜欢的唤醒词,唯一的建议就是考虑一下识别成功率。

  • 2
    Regiest Baidu AI

    In the field of cloud computing, I choose Baidu AI Open Platform as the basis. Baidu AI provides many aspects of cloud service support, such as voice, image, text, map, translation, etc. Baidu AI not only supports Chinese, but also other languages such as English. So you can use Baidu AI directly if you like.


    Before using Baidu AI, you need to register users, create applications, and then add the AI services you need to your applications. Record the APPID, API_KEY, and SUCRETY_KEY of your applications and use them later.


    Baidu AI can be invoked using HTTP or directly using SDK provided by Baidu.


    For testing purposes only, most of Baidu AI APIs offer free trials from half a year to one year.


  • 3
    Record voice

    There are two ways to record a sound: one is to trigger the recording by means of buttons, and the other is to record it fully automatically. Because I chose the full voice control mode, I chose the latter.


    The key to automatic recording is when to start recording and when to end recording. The strategy used is to set a threshold based on the volume of the sound read through pyaudio to determine when to start and end.


View all 8 instructions

Enjoy this project?



Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates