https://github.com/kmohamedalie/speaker-accent-recognition

Recognizing speaker🗣️ accent using machine learning🤖
https://github.com/kmohamedalie/speaker-accent-recognition

accent-recognition languages natural-language-understanding speech-recognition support-vector-machines

Last synced: 3 days ago
JSON representation

Recognizing speaker🗣️ accent using machine learning🤖

• Host: GitHub
• URL: https://github.com/kmohamedalie/speaker-accent-recognition
• Owner: Kmohamedalie
• License: mit
• Created: 2023-08-15T20:11:25.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-10-19T21:09:50.000Z (about 1 year ago)
• Last Synced: 2024-11-09T01:13:30.368Z (about 2 months ago)
• Topics: accent-recognition, languages, natural-language-understanding, speech-recognition, support-vector-machines
• Language: Jupyter Notebook
• Homepage: https://github.com/Kmohamedalie/Speaker-Accent-Recognition
• Size: 239 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Speaker Accent Recognition 

![image](https://github.com/Kmohamedalie/Speaker-Accent-Recognition/assets/63104472/56f983e1-114e-461b-94e4-cf6380e81135)

**Task:** recognizing speaker accent using machine learning

**Data:** [Link](https://archive.ics.uci.edu/dataset/518/speaker+accent+recognition)

**Complete JupyterNotebook:** [Link](https://github.com/Kmohamedalie/Speaker-Accent-Recognition/blob/master/Notebook/SVM%20-%20Speaker%20Accent%20Recognition.ipynb)

**Metrics:**

| Algorithm | Precision | Recall | F1-score | Accuracy |

|-----------|-----------|-------- |----------|----------|

| Support vector machine   | 81.82%    |   81.82% |  81.82%  | 81.68%  |




**Additional Information about the dataset**

Response variable: 

language = {ES, FR, GE, IT, UK, US} The six possible accents considered

Explanatory variables:

X1, X2, ..., X12 Obtained using MFCC on the original time domain soundtrack of the maximum 1s of reading of a word

Data set featuring single English words read by speakers from six different countries for accent detection and recognition