Emoticall

Emoticall will automate the performance monitoring of the call center through the speech detection of their employees during calls. It will detect the emotions of employees during their call and provide the analysis report to the admin. It will create a report of every employee that will be sent to

Project Title

Emoticall

Project Area of Specialization

Artificial Intelligence

Project Summary

Emoticall will automate the performance monitoring of the call center through the speech detection of their employees during calls. It will detect the emotions of employees during their call and provide the analysis report to the admin. It will create a report of every employee that will be sent to the admin and make it easy for the management to analyze their performance.In call centers management is required to keep check on operator’s performance. Therefore this system is devised to help monitor the performance of operator by detection of emotionsthrough speech.

The main aim of Emoticall is to automate the performance analysis of the call center. The call recordings will be available to the admin with an overall emotion analysis of the employee during the call. The admin can have the access of every call through recordings. Employees can also see their evaluation of every call. The monthly evaluation and past achievements will also be accessible by the employees. It will maintain discipline in operators and the customers will be more satisfied. 

Project Objectives

• The primary objective of emoticall is to improve man machine interface.
• The main objective of emoticall is to generate the performance reports for the operators directly, by detecting his/her emotions instead of using rating system which most of the customers do not even bother to do so.

Project Implementation Method

The first step is data collection, which is of prime importance. The model being developed will learn from the data provided to it and all the decisions and results that a developed model will produce is guided by the data. Then feature engineering is done. It is a collection of several machine learning tasks that are executed over the collected data. These procedures address the several data representation and data quality issues

The task of speech emotion detection (SED) is traditionally divided into two main parts: feature extraction and classification, as depicted in Figure. During the feature extraction stage, a speech signal is converted to numerical values using various front-end signal processing techniques such as blocking. Extracted feature vectors have a compact form and ideally should capture essential information from the signal. In the back-end, an appropriate classifier is selected according to the task to be performed.

Feature Engineering: MFCC and LSTM

Models: K Nearest Neighbors and Convolution Neural Networks 

Benefits of the Project

Automation in call centers by generating the performance reports for the operators directly, by detecting his/her emotions instead of using rating system which most of the customers do not even bother to do so.

Technical Details of Final Deliverable

.py files

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com