Hi everyone. This is my Week 1 Progress report. As the coding period has just started… haven’t started with much…but still…made some progress.
Worked on a script to keep a check on the accuracy statistics of pocketsphinx…based on the characteristics of the audio input - it’s sampling rate…chunk-size…etc. This can in turn help in accurately decoding the speech to text later on.
Made a script to record the audio from the microphone…and based on the intervals of silence…it splits the audio. As soon as the audio file is created…it pauses the recording process…and then performs the tasks to be done with the audio input…only to resume the process later.
Working on using the script mentioned in 2 in order to launch other processes… especially the games.
Works to be done during next week:
Checking audio accuracy statistics by using sophisticated audio as well as noisy audio.
Improving the voice_input part of the games already created…that is…Hangman and Spell It!
Working on launching the entire process at boot-time.
Deploy the entire thing on a pocketbeagle with the hardware. Could not start work with the board…because till now haven’t received the complete set of components.
- The accuracy of recognition of letters is very poor. Cannot think of any idea to overcome the problem.
Working repository link:
Main working repository:
Previous working repository before commencement of GSoC coding period:
I will merge all the updates in my main working repository only.