Adil Khan 1 year ago
AdiKhanOfficial #FYP Ideas

Speaker Recognition System

Speaker Recognition is the task of recognizing the speaker from his/her voice. The technique utilizes Acoustic features of speech that have found to be unique for an individual. These acoustic patterns reflect both, the anatomy and the behavioural patterns of the speaker. The pr

Project Title

Speaker Recognition System

Project Area of Specialization

Artificial Intelligence

Project Summary

Speaker Recognition is the task of recognizing the speaker from his/her voice.

The technique utilizes Acoustic features of speech that have found to be unique

for an individual. These acoustic patterns reflect both, the anatomy and the

behavioural patterns of the speaker. The problem of speaker recognition arises

in two flavours. One, where the speaker is allowed to speak only a fixed text,

called Text Dependent Speaker Recognition. Other, where the speaker is free

to say anything, called the Text Independent Speaker Recognition.

The application of such systems lie in various kinds of security systems, since

the anatomy of the vocal tract is unique for an individual. It can also enhance

the human computer interaction.

Project Objectives

The proposed project is supposed to make use of speech recognition feature in order to create a bot that could communicate and help normal person or disabled peoples to use their computer without typing and clicking.

Project Implementation Method

Digital speech is a one-dimensional time-varying discrete signal. Sound are pressure waves, and these waves can be represented by numbers over a time period. These air pressure differences communicate with the brain. Audio files are generally stored in .wav, .flac, .mp3 etc format and need to be digitized, using the concept of sampling.
The sampling frequency (or sample rate) is the number of samples (data points) per second in a round. For example: if the sampling frequency is 44 kHz, a recording with a duration of 60 seconds will contain 2,646,000 samples. In practice, sampling even higher than 10x helps measure the amplitude correctly in the time domain.

Benefits of the Project

In this project we have use machine learning algorithms for feature extraction and feature modelling. A popular machine learning approach will be used to select the most appropriate and relatively important features that will greatly help to make models for accurate classification. Then Machine learning optimization technique will be applied for obtaining the optimal solution. The basic aim of project is to design a novel, cost effective, enhanced features for the classification of speakers with improved performance and efficacy.

Technical Details of Final Deliverable

Data Collection

Preprocessing

Feature Extraction

Modeling and Training and Predicting

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Quality Education

Required Resources

Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total Hardware and Assembling Equipment15000050000
Total in (Rs) 50000
If you need this project, please contact me on contact@adikhanofficial.com
0
252
MechIn

The automotive industry in Pakistan is the one of the fastest-growing industries of the co...

1675638330.png
Adil Khan
1 year ago
Disease classification of winter crops by CNN

In agriculture sector, Pakistan is ranked in the top of the list. Various factors such as...

1675638330.png
Adil Khan
1 year ago
Service Zone

In our busiest daily routine as, everyone is engaged in his job, so no one has sufficient...

1675638330.png
Adil Khan
1 year ago
Automatic Temperature Detection System for Entrance

COVID 19 has made a huge impact on the society, the new restriction has been imposed as in...

1675638330.png
Adil Khan
1 year ago
Assignment No 3 - Construct LL(1) parser for modified CFG show moves m...

1675638330.png
Adil Khan
6 years ago