-
Speech Commands Recognize Based On MFCC Features
-
You can downlaod Google speech commands dataset from "http://download.tensorflow.org/data/speech_commands_v0.01.tar.gz"
-
I olny use four commands "no","off","on","yes". Let's call them 0, 1, 2, 3
-
Your Tensorflow version must than 2.0. Using TFRecord file for train datas.
-
It's only a simple example for speech commands recognize based on MFCC, using a cnn model. INT8 quantized.
-
If you have some question, you can contact with me. WeChat:xuelei_jian
-
TODO: Covert the model and inference it on the Cotex-M microcontroller.
-
Your star is the best encouragement for me.
-
Notifications
You must be signed in to change notification settings - Fork 1
JeanXL/MFCC-Speech-Commands-Recognize-
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Speech Commands Recognize Based MFCC Features
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published