|
UWSpace >
University of Waterloo >
Electronic Theses and Dissertations (UW) >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10012/942
|
| Title: | A Dynamic Vocabulary Speech Recognizer Using Real-Time, Associative-Based Learning |
| Authors: | Purdy, Trevor |
| Keywords: | Electrical & Computer Engineering
Speech Recognition
ASR
Artificial Intelligence
Pattern Recognition |
| Approved Date: | 2006 |
| Date Submitted: | 2006 |
| Abstract: | Conventional speech recognizers employ a training phase during which many of their parameters are configured - including vocabulary selection, feature selection, and decision mechanism tailoring to these selections. After this stage during normal operation, these traditional recognizers do not significantly alter any of these parameters. Conversely this work draws heavily on high level human thought patterns and speech perception to outline a set of precepts to eliminate this training phase and instead opt to perform all its tasks during the normal operation. A feature space model is discussed to establish a set of necessary and sufficient conditions to guide real-time feature selection. Detailed implementation and preliminary results are also discussed. These results indicate that benefits of this approach can be seen in increased speech recognizer adaptability while still retaining competitive recognition rates in controlled environments. Thus this can accommodate such changes as varying vocabularies, class migration, and new speakers. |
| Department: | Electrical and Computer Engineering |
| Degree: | Master of Applied Science |
| URI: | http://hdl.handle.net/10012/942 |
| Appears in Collections: | Faculty of Engineering Theses and Dissertations
Electronic Theses and Dissertations (UW)
|
This item is protected by original copyright
|
All items in UWSpace are protected by copyright, with all rights reserved.
|
