https://github.com/klaudiozdrava/digit-recognition

A Python project that was developed as a university assignment for the subject of Signal Processing and Voice Recognition. The goal of this assignment was to make an ASR system that predict digits from a voice signal using Neural Network.
https://github.com/klaudiozdrava/digit-recognition

audio-processing digits-recognition neural-network python pytorch spectrogram

Last synced: 17 days ago
JSON representation

A Python project that was developed as a university assignment for the subject of Signal Processing and Voice Recognition. The goal of this assignment was to make an ASR system that predict digits from a voice signal using Neural Network.

• Host: GitHub
• URL: https://github.com/klaudiozdrava/digit-recognition
• Owner: klaudiozdrava
• Created: 2022-10-18T01:37:55.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-10-18T03:35:11.000Z (over 2 years ago)
• Last Synced: 2024-11-08T13:08:09.727Z (2 months ago)
• Topics: audio-processing, digits-recognition, neural-network, python, pytorch, spectrogram
• Language: Python
• Homepage:
• Size: 15.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Digit-Recognition

A Python project that was developed as a university assignment for the subject of Signal Processing and Voice Recognition.

The goal of this assignment was to make an ASR system that predict digits from a voice signal using Neural Network.

The dataset that was used for the purpose of this assigment is AudioMNIST.

The steps of the algorithm are :

1) We train a simple Feed Forward Neural Network model using only Mel Spectogram as features. 

2) Seperate foreground from background information using REPET algorithm.

3) In the foreground signal,we extract digits information using sliding window technique.

4) Finally we feed our model with these digits and make predictions.

To run this project :

1) You should download the necessary libraries from requirement.txt and also the audio dataset.

2) Run Dataset.py first and after run Network.py.

3) Finally you should run the prediction.py and insert the file path when prompted.