Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sleeplessglory/speech-audiometry
Speech audiometry digital platform for searching videos using keywords in one's speech
https://github.com/sleeplessglory/speech-audiometry
back-end batch doxygen flask front-end python testing
Last synced: 6 days ago
JSON representation
Speech audiometry digital platform for searching videos using keywords in one's speech
- Host: GitHub
- URL: https://github.com/sleeplessglory/speech-audiometry
- Owner: sleeplessglory
- License: mit
- Created: 2023-04-07T11:29:54.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-14T10:45:58.000Z (2 months ago)
- Last Synced: 2024-09-14T21:09:39.169Z (2 months ago)
- Topics: back-end, batch, doxygen, flask, front-end, python, testing
- Language: Python
- Homepage:
- Size: 185 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Web Speech Audiometry Description
This project is a web application including speech audiometry technology. It's a desktop website providing opportunities to watch and search for videos using a speech audiometry module.
This module is able to define keywords in one's speech off the video and find those videos.
# The Algorithm
All the users can find videos based on their names or keywords containing in speech data in videos. The program find keywords in relevant videos and count the amount of keywords in each one. Then videos are being sorted by the amount of found keywords, which makes videos show as relevant as the amount of keywords within them. The more keywords are being found in speech data, the higher the video is being shown in the list of results.
# Digital platform architecture![Архитектура системы веб-сервиса](https://github.com/user-attachments/assets/d8ad4328-1bdd-49c5-aa17-c6bc2e1ec353)
# Digital platform model![Модель системы веб-сервиса](https://github.com/user-attachments/assets/2a0a23d9-7611-4ac0-87fc-6305d115d393)
# Interface of the Web Page With Results
The speech audiometry technology is being used in a program module when the keywords are typed in the corresponding search bar. One search bar is for video names, another one is for keywords.
![0](https://github.com/darkswan19/WebAppDip/assets/91571026/fcd84455-f3eb-42e2-b2dc-0a7a92450d6c)
# Unit and Application Testing
The application testing is shown in the picture above, manually being tested right on the web page. The video containing more keywords than another one is shown higher in results.
The unit testing contains functions that automatically put diverse video names and keywords to define the amount of keywords. At the end of each test the list of sorted results is being returned.
![4](https://github.com/darkswan19/WebAppDip/assets/91571026/483f8291-689d-407a-b4cd-6d48a819e933)
![5](https://github.com/darkswan19/WebAppDip/assets/91571026/af5ec2ba-3026-42fc-9cd8-65e14f926784)
# Developer Documentation
The developer documentation was made by Doxygen and the batch file included above.
All the functions of the module are described: their brief description, parameters, exceptions and what they return.
![1](https://github.com/darkswan19/WebAppDip/assets/91571026/78d3c010-d340-4f4c-9e4e-dfae500b478f)
![2](https://github.com/darkswan19/WebAppDip/assets/91571026/e722109a-6d17-4158-9263-b2e783a32a6f)
# User Documentation
Eventually, the user documentation was made to raise the awareness of how the speech audiometry technology works and all main functionalities of the web site are also described.![3](https://github.com/darkswan19/WebAppDip/assets/91571026/f6b8c88a-b760-41d9-a1b2-8b92747d3f8e)