Classifying Gender Age and Ethnicity of Voice

Project Title

Classifying Gender Age and Ethnicity of Voice

Project Area of Specialization Artificial IntelligenceProject Summary

Using the audio of a person our system would classify gender, age and ethnicity of the voice.

Project Objectives

• We will record audio signals.
• Convert audio signals to frequency matrix.
• Apply feature extraction.
• Apply component analysis.
• Do gender classification.
• Age classification.
• Ethnic group classification.
• Web development.

Project Implementation Method

In voice gathering.

• We are going to have 5 english senteces and 5 urdu sentences spoken by 70 juviniles,70 adult males. 70 adult females, 70 old males and 70 old females. Dataset had a total of 350 speakers and 3500 audios.

In classification we are going to reseach the best suitable classifier and even come up with the mixture of models to improve accuracy.

Benefits of the Project

Law enforcement agencies sometimes only have an audio to catch a criminal which is not sufficient to tell the description about the criminal. We need to narrow down our suspects by classifying the audio. Using voice classification we will conclude the gender, age groups and the ethnic group of that individual, it will be a great impact on the departments and they will be granted ease in finding that criminal and getting more information about them.

Technical Details of Final Deliverable

Final diliverrable would have a reseach paper and a web application.

Final Deliverable of the Project HW/SW integrated systemCore Industry SecurityOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	70000
Sennheiser HMD 414 headset-mounted microphone	Equipment	1	30000	30000
Breul & Kjaer 1/2	Equipment	1	40000	40000