ODYSSEY 2004 - The Speaker and Language Recognition Workshop
May 31 - June 3, 2004
The the use of several acoustic feature types, also called the multi-stream approach, has proven to be very successful in speech recognition tasks and to a certain extent in speaker authentication tasks. In this study we propose a noise-robust multi-stream text-independent speaker authentication system. This system is trained in two steps: first train the stream experts under clean conditions and then train the combination mechanism to merge the scores of the stream experts under both clean and noisy conditions. The idea here is to take advantage of the rather predictable reliability and diversity of streams under different conditions. Hence, noise-robustness is mainly due to the combination mechanism. This two-step approach offers several practical advantages: the stream experts can be trained in parallel (e.g., by using several machines); heterogeneous types of features can be used and the resultant system can be robust to different noise types (wide bands or narrow bands) as compared to sub-streams. An important finding is that a trade-off is often necessary between the overall good performance under all conditions (clean and noisy) and good performance under clean conditions. To reconcile this trade-off, we propose to give more emphasis or prior to clean conditions, thus, resulting in a combination mechanism that does not deteriorate under clean conditions (as compared to the best stream) yet is robust to noisy conditions.
Bibliographic reference. Poh, Norman / Bengio, Samy (2004): "Noise-robust multi-stream fusion for text-independent speaker authentication", In ODYS-2004, 199-206.