Web resources for language modeling in conversational speech recognition
Abstract
This article describes a methodology for collecting text from the Web to match a target sublanguage both in style (register) and topic. Unlike other work that estimates n-gram statistics from page counts, the approach here is to select and filter documents, which provides more control over the type of material contributing to the n-gram counts. The data can be used in a variety of ways; here, the different sources are combined in two types of mixture models. Focusing on conversational speech where data collection can be quite costly, experiments demonstrate the positive impact of Web collections on several tasks with varying amounts of data, including Mandarin and English telephone conversations and English meetings and lectures.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Dec 01, 2007
- Source ID
- 10.1145/1322391.1322392
Entities
People
- Andreas Stolcke
- Ivan Bulyko
- Manhung Siu
- Mari Ostendorf
- Tim Ng
- Özgür Çetin
Organizations
- BBN Technologies
- Defense Advanced Research Projects Agency
- Hong Kong University of Science and Technology
- International Computer Science Institute
- University of Washington