Nonlinear compensation and heterogeneous data modeling for robust speech recognition
The goal of robust speech recognition is to maintain satisfactory recognition accuracy under mismatched operating conditions. This dissertation addresses the robustness issue from two directions. In the first part of the dissertation, we propose the Gauss-Newton method as a unified approach to esti...
| Main Author: | |
|---|---|
| Published: |
Georgia Institute of Technology
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1853/47566 |