Speaker: Veera Venkataramani, JHU

Title: SUPPORT VECTOR MACHINES FOR AUTOMATIC SPEECH RECOGNITION IN A CODE 
BREAKING FRAMEWORK 
 
Abstract:
Code Breaking is a divide and conquer approach for sequential pattern
recognition tasks where we identify weaknesses of an existing system
and then use specialized decoders to strengthen the overall system. We
study the technique in the context of Automatic Speech
Recogniton. Using the lattice cutting algorithm, we first analyze
lattices generated by a state-of-the-art speech recognizer to spot
possible errors in its first-pass hypothesis. We then train
specialized decoders for each of these problems and apply them to
refine the first-pass hypothesis.
 
We study the use of Support Vector Machines (SVMs) as discriminative
models over each of these problems. The estimation of a posterior
distribution over hypothesis in these regions of acoustic confusion is
posed as a logistic regression problem. $Gini$SVMs, a variant of SVMs,
can be used as an approximation technique to estimate the parameters
of the logistic regression problem.
  
We first validate our approach on a small vocabulary recognition task,
namely, alphadigits. We show that the use of $Gini$SVMs can
substantially improve the performance of a well trained MMI-HMM
system. We also find that it is possible to derive reliable confidence
scores over the $Gini$SVM hypotheses and that these can be used to
good effect in hypothesis combination.
  
We will then analyze lattice cutting in terms of its ability to
reliably identify, and provide good alternatives for incorrectly
hypothesized words in the Czech MALACH domain, a large vocabulary
task. We describe a procedure to train and apply SVMs to strengthen
the first pass system, resulting in small but statistically
significant recognition improvements. We conclude with a discussion of
methods including clustering for obtaining further improvements on
large vocabulary tasks.
 
Bio: 
Veera Venkataramani received the Bachelor of Engineering degree for
the Regional Engineering College, Tiruchirappalli in May 1998. He
received the Master of Science in Engineering from the Johns Hopkins
University in May 2000. Since then he has been pursuing a Ph.D in
Electrical and Computer Engineering at the Center for Language and
Speech Processing (CLSP). under the guidance of Prof. William
Byrne. He has been an intern at Speechworks Inc.(now part of Scansoft)
and at the IBM TJ Watson Research Center. He participated in the 2000
summer research workshop in language engineering at CLSP. His research
interests include statistical modeling techniques for speech and
language engineering.