Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add GUI for speech recognition testing and improve recognition accuracy #12

Open
wants to merge 22 commits into
base: master
Choose a base branch
from
Open

Add GUI for speech recognition testing and improve recognition accuracy #12

wants to merge 22 commits into from

Conversation

petschekr
Copy link

@petschekr petschekr commented Jun 1, 2017 •
edited
Loading

  • Adds a GUI with support for:
    • Recognizing speech from a live recording
    • Recognizing speech from a .wav file
    • Recognizing speech from a folder of .wav files
    • Exporting speech recognition results to a .json file for comparison
  • Improves speech recognition accuracy by applying the recognition threshold relatively to the other matches that the engine returns. Previously, recognition results were only accepted if their probability was over 100% (minimum probability (returned by the engine as the log10 of the actual probability) was set to 0 and 10^0 = 1.00).
  • Fixes inconsistent whitespace and indentation styles in the hlpr_speech_recognition module

petschekr added 17 commits May 30, 2017 15:23
@petschekr
Fix inconsistent whitespace and indentation
0f71f29
@petschekr
Initial speech testing UI commit
b110382
@petschekr
Add testing .wav files
616f5cb
@petschekr
Update SpeechRecognizer to support reading audio from .wav files
ee58f02
@petschekr
Add method to stop speech recognition without stopping SpeechRecogniz…
d3434d0 
…er node
@petschekr
Implement starting / stopping audio recording in the UI
d2460bd
@petschekr
Simplify file loading in SpeechRecognizer
79cbda4
@petschekr
Implement opening and recording audio for speech recognition
d5542a5
@petschekr
Default open file dialog's directory to the directory of current file
7b45475
@petschekr
Improve recognition accuracy by applying threshold relatively
c67632f
@petschekr
Normalize quote style
535779e
@petschekr
Subscribe to recognizer topic and list recognized commands in the GUI
18b63cd
@petschekr
Add support for opening a folder of .wav files for recognition
f3b6265
@petschekr
Add UNKNOWN speech keyword for when the phrase can't be determined
180a90e
@petschekr
Don't error for invalid file / directory name
e90aa83
@petschekr
Ensure that speech results are correctly matched to files when openin…
2383685 
…g folder
@petschekr
Add clear and export output buttons
69860ee
@petschekr petschekr changed the title Add GUI for speech recognition testing and improve Add GUI for speech recognition testing and improve recognition accuracy Jun 1, 2017
@petschekr
Copy link
Author

Documentation: https://github.com/HLP-R/hlpr_documentation/wiki/Speech-Testing-GUI

@petschekr
Copy link
Author

@vchu Did you ever get to review this?

@petschekr petschekr requested a review from vchu August 4, 2017 18:45
@vchu
Copy link
Contributor

vchu commented Aug 4, 2017

No I didn't! Missed my radar. Thanks for pointing it out. Well definitely review this. I'll be testing speech this weekend.

@eshort
Copy link
Contributor

eshort commented Aug 6, 2017

I believe this PR is missing the travis fixes that I merged in a few days ago -- can you try pulling in the changes from master and see if the travis build works?

@petschekr
Copy link
Author

Merged in those fixes and the build now passes

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@vchu vchu Awaiting requested review from vchu

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@petschekr @vchu @eshort