Abstract | ||
---|---|---|
To reduce data storage for speaker adaptive (SA) models, in our previous work, we proposed a sparse speaker adaptation method which can efficiently reduce the number of adapted parameters by using Euclidean projection onto the L 1-ball (EPL1) while maintaining recognition performance comparable to maximum a posteriori (MAP) adaptation. In the EPL1-based sparse speaker adaptation framework, however, the adapted Gaussian mean vectors are mostly concentrated on dimensions having large variances because of assuming unit variance for all dimensions. To make EPL1 more flexible, in this paper, we propose scaled norm-based Euclidean projection (SNEP) which can consider dimension-specific variances. By using SNEP, we also propose a new sparse speaker adaptation method which can consider the variances of a speaker-independent model. Our experiments show that the adapted components of mean vectors are evenly distributed in all dimensions, and we can obtain sparsely adapted models with no loss of phone recognition performance from the proposed method compared with MAP adaptation. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1186/s13634-015-0290-2 | EURASIP Journal on Advances in Signal Processing |
Keywords | Field | DocType |
Euclidean projection onto the L1-ball, MAP adaptation, Scaled norm-based Euclidean projection, Sparse speaker adaptation | Map adaptation,Pattern recognition,Computer science,Computer data storage,Norm (social),Speech recognition,Gaussian,Artificial intelligence,Euclidean geometry,Maximum a posteriori estimation,Machine learning,Speaker adaptation | Journal |
Volume | Issue | ISSN |
2015 | 1 | 1687-6180 |
Citations | PageRank | References |
0 | 0.34 | 19 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Younggwan Kim | 1 | 17 | 6.11 |
Myung Jong Kim | 2 | 31 | 6.30 |
Hoi-Rin Kim | 3 | 102 | 20.64 |