Predictive audio/intonation of numbers model
This project would collect the data from Machine learning class 2020/2021 @ QMUL
The data would be collected by audio recognition such as 0-9(digit), 10-100(tenth), Thousand, Million, and Billion.
This project will provide two solutions which consist of Basic Solution and Advanced Solution
Basic solution would consider the model as below and using accuracy as a metric
Direcotry Structure
MLEnd-mini-project
├── dataset
│ └── XXXXXX.csv
└── XXXXX.wav
├── Basic solution
│ ├── Random Forest - MLEnd_Basic solution_RandomForest.ipynb
│ ├── Support Vector Machine - MLEnd_Basic solution_SVM.ipynb
│ ├── Naive Bayes - MLEnd_Basic solution_Naive Bayes.ipynb
├── Logistic Regression - MLEnd_Basic solution_Logistic Regression.ipynb
│── Advanced solution
│ └── (Example) XXXXX.ipynb
│ └── (Example) XXXXX.ipynb
│ └── (Example) XXXXX.ipynb
└── README.md