Voice-Signal-Authentication

This desktop app utilizes concepts of fingerprinting and spectrograms to recognize authorized individuals and grant access accordingly. It operates in two modes: Security Voice Code and Security Voice Fingerprint.

Features

Mode 1: Security Voice Code

In this mode, access is granted only if the spoken voice matches one of the predefined pass-code sentences. The following sentences are considered valid passcodes:

"Open middle door"
"Unlock the gate"
"Grant me access"

Users can choose alternative passcode sentences as long as they do not contain similar words among the three chosen sentences.

Mode 2: Security Voice Fingerprint

Access is granted to specific individuals who say the valid pass-code sentence. Users can select which individual(s) out of the original 8 users are granted access through the settings UI. Access can be granted to one or more individuals.

User Interface (UI)

The UI provides the following elements:

Button to Start Recording: Initiates the recording of the voice-code.
Spectrogram Viewer: Displays the spectrogram of the spoken voice-code.
Summary for Analysis Results:
1. Table indicating how much the spoken sentence matches each of the saved three passcode sentences.
2. Table indicating how much the spoken voice matches each of the 8 saved individuals.
Result Indicator: UI element indicating whether the algorithm results in "Access gained" or "Access denied".

Usage

Clone this repository to your local machine.
Open the project in your preferred IDE.
Run the application.
Use the provided UI to interact with the software, select operation mode, record voice-code, and view analysis results.

Contributions

Contributions to this project are welcome. If you find any issues or have suggestions for improvements, please feel free to submit a pull request or open an issue on GitHub.