Weekly Update
- Yavneeka Patel
- Apr 15, 2015
- 2 min read
PROGRESS UPDATE
*Created a dictionary:
Goal:
-the idea is to have two portions a "speech" portion and a "hardware" portion.
Progress:
-INSERT PICTURE HERE
*Worked on code for the execution of the dictionary
Goal:
-The speech portion will listen for specific words and then execute a command
Progress:
-Add hashmap to the code (this doesn't really work)
-Add .wav files to the resources folder and link them to the application (using hashmap?)
-the hardware portion will light up LEDs based on a command.
-Note: Sphinx recognizes this command set the best
Difficulties Faced:
-Speech is not 100% accurate & I cannot filter the gram file being used, so there are a lot of words the computer is listening for and it sometimes gets confused.
-Room must be very quiet for the speech recognition to work.
-I am still unsure about how to use hashmaps, but will need to figure this out ASAP, otherwise I will just use an array to store the .wav files.
*Raspberry Pi setup
Progress:
-I imaged the SD card for the Rasberry Pi to hold the Raspbian image using the command line. I followed the steps from the Raspberry Pi website.
-To log into the Raspberry Pi: username is "pi", password is "raspberry". This is universal for all Raspberry Pi's unless you have changed the username and password fields.
-To begin the graphical interface: type in "startx".
Goal:
-Add code to the Raspberry Pi
Difficulties Faced:
-Could not use package setup on lab computers because I do not have proper admin status. Talked to Luke about this, and we determined it would be possible to image the SD card using command line
-Need to hook into the projector, could not find connector cable to be able to use computer
GOALS FOR NEXT WEDNESDAY:
1. Fine tune and complete all code (have it working with Speech recognition)
2. Add the code to the Raspberry Pi
3. Insert microphone & speakers to the Raspberry Pi to get sound input and output. (TA Help Needed)
3. Add LEDs, and get hardware portion to work.
Comments