This thesis explores the use of randomized, performance-based search strategies to improve the generalization of an automatic speech recognition system based on hidden Markov models. We apply simulated annealing and random search to several components of the system, including phoneme model topologies, distribution tying, and the clustering of allophonic contexts. By using knowledge of the speech problem to constrain the search appropriately, we obtain reduced numbers of parameters and higher phonemic recognition results. Performance is measured on both our own data set and the Darpa TIMIT database.
Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:QMM.56977 |
Date | January 1992 |
Creators | Galler, Michael |
Contributors | De Mori, Renato (advisor) |
Publisher | McGill University |
Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
Language | English |
Detected Language | English |
Type | Electronic Thesis or Dissertation |
Format | application/pdf |
Coverage | Master of Science (School of Computer Science.) |
Rights | All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated. |
Relation | alephsysno: 001325404, proquestno: AAIMM87718, Theses scanned by UMI/ProQuest. |
Page generated in 0.0015 seconds