Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P2.3 |
| Session: | Speaker Adaptation |
| Time: | Tuesday, May 18, 13:00 - 15:00 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Adaptation/Normalization |
| Title: |
MPE-BASED DISCRIMINATIVE LINEAR TRANSFORM FOR SPEAKER ADAPTATION |
| Authors: |
Lan Wang; Cambridge University | | |
| | Phil Woodland; Cambridge University | | |
| Abstract: |
In this paper, we present a discriminative method for speaker adaptation, where the minimum phone error (MPE) criterion is used to estimate the discriminative linear transform (DLT), including mean and diagonal variance transforms. The I-smoothing technique is essential to improve the generalization of DLTs. Experiments on supervised adaptation for non-native speakers on the North American Business Spoke 3 task show that MPE-based DLT outperforms both MLLR and previously proposed discriminative method for transform estimation. Preliminary experiments on unsupervised DLT estimation are plotted on conversational telephone speech transcription. |
| |
| Back | |