Abstract | ||
---|---|---|
Speech recognition systems typically contain many Gaussian distributions, and hence a large number of parameters. This makes them both slow to decode speech, and large to store. Techniques have been proposed to decrease the number of parameters. One approach is to share parameters between multiple Gaussians, thus reducing the total number of parameters and allowing for shared likelihood calculation. Gaussian tying and subspace clustering are two related techniques which take this approach to system compression. These techniques can decrease the number of parameters with no noticeable drop in performance for single systems. However, multiple acoustic models are often used in real speech recognition systems. This paper considers the application of Gaussian tying and subspace compression to multiple systems. Results show that two speech recognition systems can be modelled using the same number of Gaussians as just one system, with little effect on individual system performance. |
Year | Venue | Keywords |
---|---|---|
2009 | INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | Automatic speech recognition, graphemes, subspace compression, Gaussian tying |
Field | DocType | Citations |
Compression (physics),Subspace clustering,Pattern recognition,Subspace topology,Computer science,Tying,Speech recognition,Gaussian,Artificial intelligence | Conference | 0 |
PageRank | References | Authors |
0.34 | 6 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
carmel b breslin | 1 | 0 | 0.34 |
m stuttle | 2 | 17 | 2.83 |
Kate Knill | 3 | 249 | 28.02 |
iisc assoc | 4 | 0 | 0.34 |