Title | ||
---|---|---|
Rapid signer adaptation for continuous sign language recognition using a combined approach of eigenvoices, MLLR, and MAP. |
Abstract | ||
---|---|---|
Current sign language recognition systems are still designed for signer-dependent operation only and thus suffer from the problem of interpersonal variability in production. Applied to signer-independent tasks, they show poor performance even when increasing the num- ber of training signers. Better results can be achieved with dedicated adaptation methods. In this paper, we describe a vision-based recognition system that quickly adapts to new signers. For rapid signer adaptation it employsacombinedapproachof eigenvoices,maximum likelihood linear regression, and maximum a posteriori estimation. An extensive evaluation was performed on a large sign language corpus, that contains continuous articulations of 25 native signers. The proposed adap- tation approach significantly increases accuracy even with a small amount of adaptation data. Supervised adaptation with only 10 adaptation utterances yields a recognition accuracy of 75.8%, which is a relative error rate reduction of 30.2% compared to the signer- independent baseline. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761363 | ICPR |
Keywords | Field | DocType |
speech recognition,regression analysis,sign language,hidden markov models,accuracy,estimation,gesture recognition,maximum likelihood estimation,relative error,computer vision | Recognition system,Pattern recognition,Regression analysis,Computer science,Gesture recognition,Speech recognition,Sign language,Maximum likelihood linear regression,Artificial intelligence,Maximum a posteriori estimation,Hidden Markov model,Approximation error | Conference |
ISSN | ISBN | Citations |
1051-4651 E-ISBN : 978-1-4244-2175-6 | 978-1-4244-2175-6 | 7 |
PageRank | References | Authors |
0.48 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ulrich von Agris | 1 | 77 | 3.68 |
Christoph Blömer | 2 | 7 | 0.48 |
Karl-Friedrich Kraiss | 3 | 294 | 27.33 |