Projects
Your Project can focus on creating emotional speech technologies
(text-to-speech or emotion recognition) or designing and conducting experiments
on the perception of production of emotional speech. Some example projects
from previous years:
- Collect audio from children of different ages winning and losing a game
and see if adults can distinguish those who win (happy speech) from those
who lose (sad speech).
- Create hybrid speech stimuli from tokens uttered with different emotions
(mixing pitch, loudness, duration, speaking rate,...) and see which features
of emotional speech are most reliably associated with emotions.
- Detect different emotions from Cantonese and Mandarin speakers and
compare performance of an automatic program to performance of human judges.
- Train Machine Learning algorithms on emotional speech corpora and see if
you can improve over other approaches on the same corpora
- Develop an email reader that detects emotion from text and uses the
appropriate emotional TTS system to read it to the user
Available corpora (these are available on line in /proj/speech/corpora -- to
use them you will need a CS department account):
- LDC Emotional Speech Database
- Interspeech Paralinguistic Challenge: Levels of Interest
- Interspeech Paralinguistic Challenge: Intoxication
- Columbia Deception Corpus
Your Project Proposal should explain what you propose to do, why it is
scientifically interesting, what previous work has been done in the area, what
you will accomplish by the end of the project, and how you will accomplish
this. You should also note any obstacles to your plans. (At
this stage we will mainly be interested in determining how feasible your project
is and how much you have thought about it. Your Project Report
should address all of these issues in detail, as well as providing evidence of
results and code, where applicable.) You should view this
as a draft of a contract with Prof. Hirschberg, who will discuss your project
with you on the basis of this proposal. You should submit this proposal in the
form of a linked page from a project web page. Include relevant bibliography
(with links if online) and information about and links to any resources you will
use. Submit the web page in Courseworks in a text file.