-
Notifications
You must be signed in to change notification settings - Fork 2
Implemented Hotword Detection, Improved Accuracy, Corpus Generator #1
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.
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
Open
Navbryce
wants to merge
29
commits into
parallel-ml:master
Choose a base branch
from
Navbryce:master
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Navbryce
commented
Dec 11, 2019
- Implemented a hotword detector (Listens for "Klauba") before recording and parsing speech input
- "Intelligent" voice recording after "Klauba" is detected
- Wont' start recording until silence has been broken
- Stops recording after a certain amount of continous silence
- Improved accuracy of speech recognition
- Fine-tuned the corpus (and regenerated language and lexical models)
- Created a script to autogenerate corpuses based off of sententence templates and room numbers
- Removed the pre-input noise filtering code (in the previous iteration, we noise filtered the code BEFORE we passed it to shpinx)
- Parsed speech now passed to a python script, which can distribute the text to all other code (like the movement code)
- Script won't stop running until stopped by the user
…updated decode.c to use default audio device, how the record rate was specified, and made the paths more generic (shoul be replaced by an environment variable in the future
… with snowboy. interestingly, the snowboy terminate method hangs when called
…ntinous silence. Now waits for a continous amount of silence. fixed a bug that inputted the raw audio instead of the filtered audio. decode script now infinitely loops until the user hits cntrl-c
…ller duration of silence before recording stops). Explicitly enabled noise reduction when calling sphinx. Used the raw recording instead of the noise filtered version to pass to sphinx.
…xical and language model.
…upon first detection of hotword.
… the silence detect break condition
Member
|
Can you clean the commits little bit? Seems like so many files. |
Author
|
I don't want to .gitignore or remove any of the files in the pocketsphinx or cmusphinx directories because I'm not sure which ones are required for the libraries to build. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.