Name
Abstract | ||
|---|---|---|
Jacobian Adaptation (JA) has been successfully used in Automatic Speech Recognition (ASR) systems to adapt the acoustic models from the training to the testing noise conditions. In this work we present an improvement of JA for speaker verification, where a specific training noise reference is estimated for each speaker model. The new proposal, which will be referred to as Model-dependent Noise Reference Jacobian Adaptation (MNRJA), has consistently outperformed JA in our speaker verification experiments. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1093/ietisy/e88-d.7.1767 | IEICE Transactions |
Keywords | Field | DocType |
speaker model,robust speaker veric ation,testing noise condition,specific training noise reference,jacobian adaptation,speaker verification,frequency filtering.,acoustic model,robust speaker verification,improved jacobian adaptation,model-dependent noise reference jacobian,automatic speech recognition,speaker verification experiment,new proposal | Speaker verification,Model matching,Jacobi method,Pattern recognition,Jacobian matrix and determinant,Adaptive method,Computer science,Speech recognition,Speaker recognition,Artificial intelligence,Frequency filtering | Journal |
Volume | Issue | ISSN |
E88-D | 7 | 1745-1361 |
Citations | PageRank | References |
1 | 0.38 | 3 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jan Anguita | 1 | 37 | 4.30 |
| Javier Hernando | 2 | 712 | 113.62 |
| Alberto Abad | 3 | 76 | 10.30 |