| COURSE NUMBER | -- | ECE: 18799D | LTI: 11756 |
| LTI students can also register for this course as a lab course |
| Credits: | 12 | |
| Timings: | 4:30 p.m. -- 5:50 p.m. | |
| Days: | Mondays and Wednesdays | |
| Location: | GHC 4102 |
| Prerequisites: |
| Mandatory: Linear Algebra. Basic Probability Theory. |
| Recommended: Signal Processing. |
| Coding Skills: This course will require significant programming form the students. Students must be able to program fluently in at least one language (C, C++, Java, Python, LISP, Matlab are all acceptable). |
This is a project-based course.
| PROJECTS PAGE |
Voice recognition systems invoke concepts from a variety of fields including speech production, algebra, probability and statistics, information theory, linguistics, and various aspects of computer science. Voice recognition has therefore largely been viewed as an advanced science, typically meant for students and researchers who possess the requisite background and motivation.
In this course we take an alternative approach. We present voice recognition systems through the perspective of a novice. Beginning from the very simple problem of matching two strings, we present the algorithms and techniques as a series of intuitive and logical increments, until we arrive at a fully functional continuous speech recognition system.
Following the philosophy that the best way to understand a topic is to work on it, the course will be project oriented, combining formal lectures with required hands-on work. Students will be required to work on a series of projects of increasing complexity. Each project will build on the previous project, such that the incremental complexity of projects will be minimal and eminently doable. At the end of the course, merely by completing the series of projects students would have built their own fully-functional speech recognition systems.
Grading will be based on project completion and presentation.
The first class will be on 19th Jan, Wednesday
| Class 1 | 19 Jan 2011 | Introduction | Slides | ||
| Class 2 | 24 Jan 2011 | Data capture. | Slides | ||
| Class 3 | 26 Jan 2011 | Feature Computation | Slides | ||
| Class 4 | 31 Jan 2011 | Dynamic programming for string alignment. | Slides | Assignment 2 | |
| Class 5 | 2 Feb 2011 | Project presentations: Data capture and feature computation | |||
| Class 6 | 7 Feb 2011 | Dynamic programming for speech recognition | Slides | ||
| Class 7 | 9 Feb 2011 | From templates to HMMs | Slides | ||
| Class 8 | 14 Feb 2011 | HMMs | Slides | ||
| Class 9 | 16 Feb 2011 | Project presentations. | Assignment 3 | ||
| Class 10 | 21 Feb 2011 | HMMs continued from class 8 | Slides | ||
| Class 11 | 23 Feb 2011 | No class | |||
| Class 12 | 28 Feb 2011 | Continuous speech | Slides | ||
| Class 13 | 2 March 2011 | Project presentations. | Assignment 4 | ||
| Class 14 | 14 Mar 2011 | Grammars | Slides | ||
| Class 15 | 16 Mar 2011 | Backpointer table. Training from continuous speech. | Slides | ||
| Class 16 | 21 Mar 2011 | Project presentations. | Assignment 5 | ||
| Class 17 | 23 Mar 2011 | Ngram models. | Slides | ||
| Class 18 | 28 Mar 2011 | Ngram Models 2 | Slides | ||
| Class 19 | 30 Mar 2011 | Class cancelled | |||
| Class 20 | 4 Apr 2011 | Project Presentations | Assignment 6 | ||
| Class 21 | 6 Apr 2011 | Subword Units | Slides | ||
| Class 22 | 11 Apr 2011 | State tying | Slides | Assignment 7 | |
| Class 26 | 25 Apr 2011 | Adaptation | Assignment 8 |