Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Speaker Identification and Verification Using Eigenvoices
Olivier Thyes, Roland Kuhn, Patrick Nguyen, Jean-Claude Junqua
Panasonic Technologies Inc., Speech Technology Laboratory
Santa Barbara, CA, USA
Gaussian Mixture Models (GMMs) have been successfully applied
to the tasks of speaker ID and verification when a large
amount of enrolment data is available to characterize client speakers.
However, there are many applications where
it is unreasonable to expect clients to spend this much time training
the system. Thus, we have been exploring the performance
of various methods when only a sparse amount of enrolment data
is available. Under such conditions, the performance of GMMs
deteriorates drastically. A possible solution is the "eigenvoice"
approach, in which client and test speaker models are confined
to a low-dimensional linear subspace obtained previously from a
different set of training data. One advantage of the approach is
that it does away with the need for impostor models for speaker
After giving a detailed description of the eigenvoice approach,
the paper compares the performance of conventional GMMs on
speaker ID and verification with that of GMMs obtained by means
of the eigenvoice approach. Experimental results are presented to
show that conventional GMMs perform better if there are abundant
enrolment data, while eigenvoice GMMs perform better if
enrolment data are sparse. The paper also gives experimental results
for the case where the eigenspace is trained on one database
(TIMIT), but client enrolment and testing involve another (YOHO).
For this case, we show that performance improves if an environment
adaptation technique is applied to the eigenspace. Finally,
we discuss priorities for future work.
Thyes, Olivier / Kuhn, Roland / Nguyen, Patrick / Junqua, Jean-Claude (2000):
"Speaker identification and verification using eigenvoices",
In ICSLP-2000, vol.2, 242-245.