https://github.com/ztrimus/speech-emotion-recognition

Predicting various emotion in human speech signal by detecting different speech components affected by human emotion.
https://github.com/ztrimus/speech-emotion-recognition

audio-files colab-notebook convolutional-neural-networks data-science deep-learning emotion-detection emotion-recognition jupyter-notebook keras librosa lstm natural-language-processing neural-network python3 pytorch rnn speech-emotion-recognition speech-recoginition supervised-learning voice

Last synced: about 14 hours ago
JSON representation

Predicting various emotion in human speech signal by detecting different speech components affected by human emotion.

• Host: GitHub
• URL: https://github.com/ztrimus/speech-emotion-recognition
• Owner: Ztrimus
• Created: 2019-06-12T17:11:30.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-06-21T22:08:41.000Z (over 2 years ago)
• Last Synced: 2024-04-18T22:18:58.025Z (9 months ago)
• Topics: audio-files, colab-notebook, convolutional-neural-networks, data-science, deep-learning, emotion-detection, emotion-recognition, jupyter-notebook, keras, librosa, lstm, natural-language-processing, neural-network, python3, pytorch, rnn, speech-emotion-recognition, speech-recoginition, supervised-learning, voice
• Language: Jupyter Notebook
• Homepage:
• Size: 19.4 MB
• Stars: 44
• Watchers: 2
• Forks: 28
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Speech Emotion Recognition

==========================

Project source can be downloaded from https://github.com/SBZed/speech-emotion-recognition.git

Author & Contributor List

--------------------------

Saurabh Zinjad

All other known bugs and fixes can be sent to *"[email protected]"* with subject *"speech emotion recognition Suggestion"*.

Reported bugs/fixes will be submitted to correction.

## Basic Idea :

Our machine learning model tries to detect and predict various emotion in speech signal or human audio by detecting different features and component of speech affected by human emotion. Emotion detection from the speech is a relatively new field of research. Here, we are trying a new approach or ways to contribute towards emotion recognition research.

## Presentation :

To get familiar and comfortable with project concept and outcomes please refer to [this presentation](https://prezi.com/view/UmLEHdSkpPpiZUGSQ71k/).

## Video Explanation [YouTube] :

If you want an explanation for the project [watch this video](https://www.youtube.com/watch?v=yvxpxcncSGs&t).

## Want to see result quickly without any installation :

1. Go to this **[google drive link](https://drive.google.com/open?id=1vVZ0uq5Uwd27RsODuyabuJePtDcCsbr9).**

2. Open **[speech_emotion_recognition.ipynb](https://colab.research.google.com/drive/1sfa3fN9W0nExpGwIwaX36arm1xYkH2PN)** notebook. it's main code for project.

3. For live demonstration or detecting your Speech emotion, Open **[live_demo_speech_emotion_recognition.ipynb](https://colab.research.google.com/drive/1LXVTlNvr8WJbaBnVbw_NbInV8wTrbOM1)** notebook. Just keep two things in mind. First, You need to record your audio in very silent room without any noise.And secondly, Model is not perfect, Show the great result for Disgust, fear, Anger, Sad. But shows poor result for surprise, Happy.

## How to run file :

To implement this project on your Machine

1. Clone this repository.

2. Go to terminal and type `pip install -r requirements.txt`.

3. Then open ./Code/main_speech_emotion_recognition.ipynb and run it.

## Bugs :

## Limitation and Further growth : 

1. Need to record audio in clear and silent environment.

2. Dataset is not accurate and prominant. Even, human ear can't detect accurate emotion for some audios. **Need Promising dataset.**