Abstract / truncated to 115 words (read the full abstract)

The thesis deals with automatic interpretation of naturally spoken utterances for limited-domain applications. Specifically, the problem is examined by means of a dialogue system for an airport information application. In contrast to traditional two-stage systems, speech recognition and semantic processing are tightly coupled. This avoids interpretation errors due to early decisions. The presented one-stage decoding approach utilizes a uniform, stochastic knowledge representation based on weighted transition network hierarchies, which describe phonemes, words, word classes and semantic concepts. A robust semantic model, which is estimated by combination of data-driven and rule-based approaches, is part of this representation. The investigation of this hierarchical language model is the focus of this work. Furthermore, methods for modeling out-of-vocabulary words ... toggle 18 keywords

hierarchical language model statistical language model speech interpretation speech understanding speech recognition spoken dialogue one-stage decoding robust semantic modeling weighted transition network hierarchy out-of-vocabulary words oov words semantic tree tree matching semantic tree node accuracy uniform knowledge representation natural speech smoothing n-gram

Information

Author
Thomae, Matthias
Institution
Technische Universität München
Supervisor
Publication Year
2006
Upload Date
Oct. 8, 2008

First few pages / click to enlarge

The current layout is optimized for mobile phones. Page previews, thumbnails, and full abstracts will remain hidden until the browser window grows in width.

The current layout is optimized for tablet devices. Page previews and some thumbnails will remain hidden until the browser window grows in width.