Please use this identifier to cite or link to this item:
Title: An iPhone application : audio emotion recognition
Authors: Quek, Wei Yang
Keywords: DRNTU::Engineering::Computer science and engineering::Computer applications
Issue Date: 2015
Abstract: Recognition of the human emotion by machines have been studied for a number of years due to its far reaching and beneficial effects for many industries, especially the healthcare industry. Recent development of machine learning have seen the rise of a new area that is Deep Learning. This method trumps the traditional ones due to its potential for higher accuracy. However, this requires a huge amount of data before its benefits can be observed, and its accuracy increases with increasing amount of data. This project aims to leverage on the rise of the mobile industry by developing an iPhone Emotion Recognition application which will also be deployable for PCs and other Mobile devices. With this, users will be able to use this application anywhere conveniently on their mobile devices to predict emotions, and upload their own data. This will allow the collection of more data as users can easily upload their audio files and emotions labels which can then increase the accuracy of the deep learning algorithm. The report will detail the development of the system, starting from the specifications of the system’s requirements and design objective. It will examine both the client side, where the user operate on a clean, user-friendly User Interface, and the server side, where the processing of the prediction take place in a C++ executable program. It will also discuss the rationale behind decisions made throughout the development and the challenges faced at each stage. Finally, it will present the result of the working product at the end. Especially with recognition of emotions by machines being a relatively new topic, improvements can still be made to the system. This report will conclude with the discussion of some of the future work that can be done.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Quek Wei Yang FYP Amended Report.pdf
  Restricted Access
FYP Report2.47 MBAdobe PDFView/Open

Page view(s)

checked on Sep 27, 2020

Download(s) 20

checked on Sep 27, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.