| Paper: | SP-L2.3 | ||
| Session: | Modeling Approaches in Speaker Recognition | ||
| Time: | Wednesday, May 19, 10:10 - 10:30 | ||
| Presentation: | Lecture | ||
| Topic: | Speech Processing: Speaker Recognition | ||
| Title: | DISCOVERING RELATIONS AMONG DISCRIMINATIVE TRAINING OBJECTIVES | ||
| Authors: | Qi Li; LcT, Inc. | ||
| Abstract: | In this paper, the relations among several discriminative training objectives for speech and speaker recognition, language processing, and dynamic pattern recognition are derived and discovered through theoretical analysis. Those objectives are the minimum classification error (MCE), maximum mutual information (MMI), minimum error rate (MER), and a recently proposed generalized minimum error rate (GMER) objectives. The results show that all the objectives are related to the a posteriori probability and error rates, and the MCE and GMER objectives are more general and flexible than the MMI and MER objectives. These results can help in understanding the discriminative objectives, in improving recognition performances, and in discovering new training algorithms jointly with objectives. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops