Research Interests
·
eDrama
Ø
Introduction
Ø
Useful links
·
Speech Recognition
Ø Introduction
Ø Publications
·
Software Engineering
eDrama
Introduction
I am
currently working as a research fellow for e-drama project.
E-drama is a computer technology based on online drama improvisation tool
designed for various applications (training, education, etc). It helps inspire
creativity through role-play. It is designed to be easily customizable. This
gives e-drama great potential in all areas of learning.
The
springboard for our own research is an existing e-drama system (edrama) created
by Hi8us Midlands Ltd (http://www.edrama.co.uk), a charitable company. This
system has been used in schools for creative writing, careers advice and teaching
in a range of subject areas such as history. Hi8us’ experience with edrama
suggests that the use of e-drama helps school children lose their usual
inhibitions about drama improvisation, because they are not physically present
on a stage and are anonymous. It permits a group of young people to jointly
participate in live drama improvisation online. The participants can be in the
same room or geographically separated.
We
report work in progress on adding affect-detection to an existing e-drama
program. Previous e-drama system allows a human director to monitor
improvisations and make interventions, for instance in reaction to excessive,
insufficient or inappropriate emotions in the characters’ speeches. Within an
endeavour to partially automate directors’ functions, and to allow for
automated affective bit-part characters, we have developed a prototype
affect-detection module. It is aimed at detecting affective aspects (concerning
emotions, moods, rudeness, value judgments, etc.) of human-controlled characters’
textual “speeches”. The detection is necessarily relatively shallow, but the
work accompanies basic research into how affect is conveyed linguistically. A
distinctive feature of the project is a focus on the metaphorical ways in which
affect is conveyed.
Speech
Recognition
Introduction
I am also interested in Speech
Recognition by using Feature-based approach----Pseudo-Articulatory
Representations (PARs).
Automatic recognition of speech by machine
has been a goal of research for more than four decades. It has gained an
appreciation for the amount of progress achieved over this period. And there
have been quite a lot of attempts for the automatic speech recognition by
machine, though we’re far from achieving the desired goal of a machine that can
understand spoken discourse on any subject by all speakers in all environments.
Although the acoustic-phonetic
approach is indeed viable and has been studied in great depth for more than 40
years, it has not achieved the same success as have alternative methods. The
real problem with this approach is the difficulty in getting a reliable phoneme
lattice for the lexical access stage. On the other hand, speech recognition by
computer typically employs probabilistic models (Hidden Markov Models) to
constrain the putative sequences of segments recovered from the signal. The
technique is powerful, but ignores details of the vocal tract (co-articulatory
effects) and linguistic processes (e.g. morpho-phonemic constrains). A
promising approach is to develop a computational model for processing speech in
a non-segmental way by using Pseudo-Articulatory Representations (PARs) which
represent linguistic generalizations and idealizations of articulation and the
articulator positions.
This research leads to a more
plausible level of automatic speech recognition and shall contribute to the
knowledge of phonetics and constitutes a part of the bigger enterprise to
understand human behaviour.
Information
updated on 10th Mar 2003