Merlin M'Cloud - CSC461 Final Report.pdf

Merlin M’Cloud

V00946224

CSC 461

December 11, 2023

Table of Contents

1. Introduction 3

2. Background 3

2.1. The Importance of Accessibility in Multimedia 3

2.2. Evolution of Captioning Technologies 4

3. Automatically Generated Captioning for Video 4

3.1. Overview of Captioning Systems 4

3.2. Core Components of Captioning Systems 5

3.2.1. Acoustic Model 5

3.2.2. Language Model 6

3.2.3. Decoder 7

3.3. Training Data and Supervised Learning 7

4. Machine Learning Algorithms in Automatically Generated Captioning 7

4.1. Convolutional Neural Networks (CNNs) 7

4.2. Recurrent Neural Networks (RNNs) 8