Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P15.15 |
| Session: | Robustness in Noisy Environments |
| Time: | Friday, May 21, 15:30 - 17:30 |
| Presentation: |
Poster (ICASSP 2003 Presentation) |
| Topic: |
Speech Processing: Large Vocabulary Recognition/Search |
| Title: |
AUTOMATIC SET-UP FOR SPEECH RECOGNITION ENGINES BASED ON MERIT OPTIMIZATION |
| Authors: |
Gustavo Hernandez-Abrego; Sony Electronics, Inc. | | |
| | Xavier Menendez-Pidal; Sony Electronics, Inc. | | |
| | Thomas Kemp; Sony International Europe | | |
| | Katsuki Minamino; Sony Corporation | | |
| | Helmut Lucke; Sony Corporation | | |
| Abstract: |
We propose an automatic method to set-up the several parameters that define the behavior and performance of a typical speech recognition engine. Such parameters include weights and beam widths among others. Our method is based on the definition of a merit function. Here, merit is understood as an intuitive notion of recognition performance based on both recognition accuracy and computation time. A convenient definition of merit allows to apply an optimization procedure to define a convenient set-up for the recognizer with little human intervention. The method is applied to adjust the recognition parameters of two different LVCSR applications, one in American English and another in Japanese. |
| |
| Back | |