https://github.com/ihabbendidi/trigger-word-detection
An implementation of trigger word detection using keras, for detecting digits spoken in an audio
https://github.com/ihabbendidi/trigger-word-detection
audio deep-learning detection fourier-transform gru keras precision python rnn spectograms speech-recognition trigger trigger-word-detection wave
Last synced: 6 months ago
JSON representation
An implementation of trigger word detection using keras, for detecting digits spoken in an audio
- Host: GitHub
- URL: https://github.com/ihabbendidi/trigger-word-detection
- Owner: IhabBendidi
- Created: 2019-12-18T22:02:21.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2020-01-09T18:04:55.000Z (over 5 years ago)
- Last Synced: 2025-02-09T08:25:18.269Z (8 months ago)
- Topics: audio, deep-learning, detection, fourier-transform, gru, keras, precision, python, rnn, spectograms, speech-recognition, trigger, trigger-word-detection, wave
- Language: Jupyter Notebook
- Homepage:
- Size: 10.9 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Trigger word detection model
## Context
This is an implementation of a deep learning model for trigger word detection. The model enables, after training, to detect a trigger word mention in a speech. The model is currently trained using a digits dataset, and is being improved upon using precision and F1 scores criterias. Any improvements are very welcomed.
## Advancement
The model's precision and F1 score are being improved further.
## How to Run
Require [Python 3.5+](https://www.python.org/ftp/python/3.6.4/python-3.6.4.exe) and [Jupyter notebook](https://jupyter.readthedocs.io/en/latest/install.html) installed
### Install required libraries
The first cells of the notebook contain the installation scripts, as well as scripts for downloading the dataset necessary for training. They could be run in succession the take care of this phase.
### Real-time demo
In the project directory start a command line, then run command
```
jupyter notebook
```
Open the main notebook in this repository.