[Project Addition] Emotion recognition from Speech

[JashwanthSA]

ML-Crate Repository (Proposing new issue)

🔴 Project Title : Emotion Recognition from Speech
🔴 Aim : To predict Emotion from audio files
🔴 Dataset : https://www.kaggle.com/datasets/ejlok1/toronto-emotional-speech-set-tess
🔴 Approach : I would use the TESS dataset to train the LSTM model and plot the results in a graph.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

🔴🟡 Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name : Jashwanth SA
• GitHub Profile Link : https://github.com/JashwanthSA
• Participant ID (If not, then put NA) : NA
• Approach for this Project :
  • Load audio files from the TESS dataset
  • Feature Extraction
  • Train the LSTM model
  • Plot the results
• What is your participant role? SSOC '24

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

Hi @JashwanthSA it's a nice problem statement, but in this repository we always build 5-6 models for any dataset and then check the most fitted model based on the accuracy scores. You need to upgrade your approach as per the needs of this repo.

[JashwanthSA]

Fine @abhisheks008 , haven't thought about it. I will upgrade my approach and let you know when I'm ready.

[Harshit-code-tech]

i would like to grap it....
and speaking of models.. i will use cnn, lstm, hybrid,simplernn... and in performance optimizer...
Adam, RMSprop, Adagrad, Adadelta, Adamax, Nadam, SGD
and instead of tess.. i will use 4 dataset...
tess(dataset already mentioned...)
,ravdess,(https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-speech-audio)
savee,(https://www.kaggle.com/datasets/ejlok1/surrey-audiovisual-expressed-emotion-savee)
crema..(https://www.kaggle.com/datasets/ejlok1/cremad)
and i will make a gui so that it be esaily interective.. speaking of accuracy.. will try to achieve 70%..

and if there is any more model..please do mention.. it would be great help

[abhisheks008]

To be honest pure deep learning projects are not meant to be for this repository. Hence I have decided to close this issue as this will not fit the genre of the repository.