 |
Sixth International Conference on Spoken Language Processing
(ICSLP 2000)
Beijing, China
October 16-20, 2000 |
 |
Towards Robust Telephony Speech Recognition in Office and Automobile Environments
Subrata Das, David Lubensky
IBM Thomas J. Watson Research Center,
Yorktown Heights, NY, USA
This study is concerned with improving the robustness of our
telephony speech recognition system. Our previous
implementation of this system handled both landline and cellular
speech produced in a relatively quiet environment, such as in
a regular oce. However, it was found to be unduly vulnerable
to background noise. In particular, we wanted to improve
the accuracy of the system in the environment of a moving
automobile, without impacting its performance in a quieter
background. We collected samples of automobile noise under
various operating conditions. We used these noise files
to artificially generate noisy training data. We applied MAP
adaptation procedure to study the value of such noisy training
data and found that it helped to improve the robustness of
our telephony speech recognition system. In a related study,
we also investigated performance scores as a function of the
total number of vocabulary entries in the system, as this has
implications for a practical system implementation.
Full Paper
Bibliographic reference.
Das, Subrata / Lubensky, David (2000):
"Towards robust telephony speech recognition in office and automobile environments",
In ICSLP-2000, vol.2, 955-958.