 |
Greg
Kochanski |
 |
Research
The thread linking all of my research projects is that I build
and solve computational models of complex systems. My research is
in computational phonetics, learning about the strategies we use
to produce speech. Since speech and language are complicated
things, this involves large experiments and data sets.
My work tends to be in the overlap of Linguistics, Psychology
and Computer Science.
- My
Papers.
- I am currently principal investigator on two ESRC -funded research projects.
One looks
at the strategies that we employ to pronounce new words that
we've never spoken before. (Starts September 2008.) The other
investigates differences in rhythm between English dialects and
among other languages. (Starts August 2008.)
- My current project involves testing speech recognition
systems on the conversational parts of the British National Corpus. The
BNC has data that is almost unobtainable in these days of
careful ethics approval and release forms. It contains
conversations recorded by people who wore tape recorders as
they went about their normal business. capturing the chaos of
day-to-day speech. The BNC has been available as transcribed
text, but so far the speech in it has been inaccessible. We're
currently working on aligning the text to the speech.
- Mental
Representations of Intonation
- Neurobiology and Biomechanics of Speech [Prosody]
[Articulation]
- The IViE
corpus, data I've used for research into speech intonation.
[ESRC page for that project]
- Less Recent Research
- Collaborations
- Much of the source code
that I've written is open-source and freely available. It tends
to be signal processing code, code for optimizations and
classifiers, and whatever I've needed. At the moment,
documentation is scanty.
- Miscellaneous Questions
and Answers.