Project Handout

Final report due Wednesday, April 26 at 5pm. Late reports will suffer the usual late fees and penalties.

Your final project consists of a significant portion of the grade in this class. Important dates are as follows:

• By Wednesday, April 12, 5pm. Email the instructor a description of your proposed project (at least one paragraph in length). (In your email, include a link to a webpage that contains the text.)
• From that day onward, each Wednesday until the final day of class, each of you should email a description of your progress for the week.
• Oral Presentations: Each you will give a very short 5 minute presentation on your accomplishments. We will have presentations the last four days of class: April 19, 21, 24 and 26.
• Final project reports are due on the last day of class, April 26, 2000 at 5pm. All late penalties will apply.

Your final grade for the project will be based on the on-time completion and quality of each of the above items.

Project Presentation

You will not be graded on how good a speaker you are, but on the work you have done and how well you prepared for the talk. Powerpoint presentations with audio demonstrations are strongly encouraged. (Be prepared to run your code on a surprise voice file that you have not seen before). Presentations should get better with each day since later students have had more time to prepare. Students presenting earlier will get special brownie points. Everyone will attend class each of the four days of student presentations. Please let the instructor know in advance if you cannot attend.

Project Report

Your final project report will be a web page-you do not need to print it out. Just email the address to the instructor. Most word processors are capable of outputting html code so this should not be a big hassle. A big advantage of using a webpage for your report is that you can include color figures and examples of sounds that you use or produce. If you have never designed a webpage before, this is your opportunity to learn. The report should be written as if it were to be submitted to a conference and therefore should contain the following components:

1.

A concise description of the problem.

2.

A summary of previous solutions to the problem. You should include at least one reference to a paper you have read (not a textbook).

3.

A detailed description of your solution to the problem.

4.

Matlab simulation results.

5.

A discussion of the significance of these results and how your solution differs from previous attempts.

6.

The appendix should contain complete MATLAB codes, messy derivations and any other information too detailed to keep in the main body.

Project Topics

You are strongly encouraged to come up with your own idea for a project based on your own experience. Extra points for novelty and creativeness. Projects should roughly fall under one of the four major topics in this course: 1) Speech synthesis, 2) short-term speech processing, 3) speech coding, and 4) speech recognition but your instructor is willing to consider all proposals. You are also strongly encouraged to work on two-person projects. Two-person teams need only turn in one project report and send one email per week, but remember that a two-person project is expected to be twice as much work as a one-person project.

Just a few of the possible topics include:

1.

Implement a speech synthesis algorithm more sophisticated than we implemented in HW#1.

2.

More accurate pitch detection or formant estimation procedures.

3.

In matlab, Implement a speech coder more sophisticated than LPC-10E.

4.

Implement a simpler coder to work in real-time between two PCs.

5.

Voice warping: to change the pitch or other quality of a speech signal. For example, change a voice signal to sound like Mickey Mouse.

6.

Real-time DSP implementation of any of the algorithms related to this class.

7.

Noise filtering: clean the noise from a speech signal assuming only a single speaker.

8.

Audio-based video playback for internet teaching: produce a video of a speaker's face given only audio. This required a training set video.

9.

DTW (easy) or HMM (difficult) based speech recognition.

10.

Investigate various feature detection techniques for phoneme recognition (cepstrum, LPC, mel-scale, reflection coefficients etc.)

11.

Speech recognition applied to any particular application (controlling a robot, telephone number lookup, stock report, etc)

12.

Combine adaptive filters or neural networks with any of the themes in the course.

13.

An unacceptable project would be to demo a commercial speech recognition program. A better project would be to preprocess the speech to improve the recognition performance of this program.

14.

Speaker, gender, or language detection from speech.

You are welcome (as always) to email to talk to the instructor about your project ideas.