TY - GEN
T1 - Spoken document classification with SVMs using linguistic unit weighting and probabilistic couplers
AU - Lurgel, Uri
AU - Rigoll, Gerhard
PY - 2004
Y1 - 2004
N2 - The task addressed by this paper is spoken document classification (SDC) of German TV news with Support Vector Machines (SVMs). It shows the benefits of weighting different linguistic units when combined into one feature vector. Further experiments show that probabilistic SVMs (pSVMs) with recently introduced couplers perform well on a SDC task. New couplers for multi-category classification, both for pSVMs and non-pSVMs, will be discussed. They are easy to implement and show good and promising results. It turns out that using the distance Instead of the decision value can be favorable. Theoretical justification is given for our approaches, and some results are explained theoretically.
AB - The task addressed by this paper is spoken document classification (SDC) of German TV news with Support Vector Machines (SVMs). It shows the benefits of weighting different linguistic units when combined into one feature vector. Further experiments show that probabilistic SVMs (pSVMs) with recently introduced couplers perform well on a SDC task. New couplers for multi-category classification, both for pSVMs and non-pSVMs, will be discussed. They are easy to implement and show good and promising results. It turns out that using the distance Instead of the decision value can be favorable. Theoretical justification is given for our approaches, and some results are explained theoretically.
UR - http://www.scopus.com/inward/record.url?scp=10044243836&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2004.1334347
DO - 10.1109/ICPR.2004.1334347
M3 - Conference contribution
AN - SCOPUS:10044243836
SN - 0769521282
T3 - Proceedings - International Conference on Pattern Recognition
SP - 667
EP - 670
BT - Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
A2 - Kittler, J.
A2 - Petrou, M.
A2 - Nixon, M.
T2 - Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
Y2 - 23 August 2004 through 26 August 2004
ER -