Sixth International Conference on Spoken Language Processing
October 16-20, 2000
HMM-Based Echo and Announcement Modeling Approaches for Noise Suppression Avoiding the Problem of False Triggers
Rathinavelu Chengalvarayan, David L. Thomson
Speech Processing Group,
Lucent Speech Solutions Department,
Lucent Technologies, Naperville, IL, USA
In the past, we proposed an HMM-based residual echo modeling
technique that proved to be effective in eliminating false triggering
and enhanced the recognition of valid keyword speech. The
narrow training strategy based on single recorded prompt made
the echo model a better discriminator, though it has the possible
drawback of requiring retraining if the prompt changes. To overcome
this intrinsic problem, we consider building a general echo
model that is trained over many sentences from varied voices.
The experimental results show that the multiple echo models in
conjunction with suitable filler model to represent the extraneous
speech not only provide good recognition accuracy but also
yield better out-of-vocabulary rejection.
Chengalvarayan, Rathinavelu / Thomson, David L. (2000):
"HMM-based echo and announcement modeling approaches for noise suppression avoiding the problem of false triggers",
In ICSLP-2000, vol.1, 754-757.