A Survey on Acoustic Modeling in Automatic Speech Recognition

PhD Qualifying Examination


Title: "A Survey on Acoustic Modeling in Automatic Speech Recognition"

Mr. Guoli Ye


Abstract:

As the key component, acoustic model plays an important
role in automatic speech recognition system. However, the
performance of acoustic model still can not meet the requirement of
many advanced applications, let alone being comparable with humans.

As an acoustic model, hidden Markov model (HMM) has dominated the
field for more than 30 years for its power to model temporal speech
sequences and computational efficiency. However, the first-order
Markov chain and the conditional independent assumptions of HMM,
which are made to simplify the computation, also limit the modeling
power. Various alternative acoustic models are proposed in history
with the purpose to beat HMM in either recognition accuracy or
computational cost.

By reviewing the history of the acoustic model development in this
survey, we aim to learn the experience and lessons from the past.
More importantly, we hope to identify the potential directions for
further research in acoustic modeling.


Date:     		Wednesday, 14 January 2009

Time:                   3:30p.m.-5:30p.m.

Venue:                  Room 3501
 			lifts 25-26

Committee Members:      Dr. Brian Mak (Supervisor)
 			Prof. Fangzhen Lin (Chairperson)
 			Dr. James Kwok
 			Dr. Nevin Zhang


**** ALL are Welcome ****