https://github.com/kanishknavale/speech-emotion-recognition
A simple CNN-LSTM deep neural model using Tensorflow to classify emotions from a speech dataset
https://github.com/kanishknavale/speech-emotion-recognition
cnn deep-learning lstm speech-dataset speech-emotion-recognition tensorflow
Last synced: about 1 year ago
JSON representation
A simple CNN-LSTM deep neural model using Tensorflow to classify emotions from a speech dataset
- Host: GitHub
- URL: https://github.com/kanishknavale/speech-emotion-recognition
- Owner: KanishkNavale
- License: gpl-3.0
- Created: 2021-01-26T13:24:10.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2022-06-01T18:22:22.000Z (about 4 years ago)
- Last Synced: 2025-04-02T02:02:52.932Z (about 1 year ago)
- Topics: cnn, deep-learning, lstm, speech-dataset, speech-emotion-recognition, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 109 KB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Speech-Emotion-Recognition
A simple CNN-LSTM deep neural model using Tensorflow to classify emotions from speech dataset
## Table of contents
* Reading the 'train.json' file
* Download link: www.kaggle.com/dataset/1ef5f65351c643f6d2fb0becc9993b73be3130090e234fa88f9307ef18b9de78
* Rescaling the features
* Creating train & validation data splits
* Defining the DNN model
* Model training
* Evaluating Results
## Overview
* Training Log,
* Results,
## Dependencies
Install dependencies using:
```bash
pip3 install -r requirements.txt
```
## System Requirements
* The notebook is executed online on kaggle.com with a GPU accelerator.
* To run it locally on a PC, 16GB of RAM is needed.
## Challenge
* Boost the 'Validation Accuracy' by Model modification or Data Augmentation
## Contact
* email: navalekanishk@gmail.com