Sciweavers

NAACL
1994
13 years 4 months ago
On Using Written Language Training Data for Spoken Language Modeling
We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size...
Richard M. Schwartz, Long Nguyen, Francis Kubala, ...
NAACL
1994
13 years 4 months ago
A Hybrid Approach to Adaptive Statistical Language Modeling
We desert'be our latest attempt at adaptive language modeling. At the heart of our approachis a Maximum Entropy(ME) modelwhich inc.orlxnatesmanyknowledgesources in a consiste...
Ronald Rosenfeld
NAACL
1994
13 years 4 months ago
Recent Improvements in the CMU Spoken Language Understanding System
We have been developing a spoken language system to recognize and understand spontaneous speech. It is difficult for such systems to achieve good coverage of the lexicon and gramm...
Wayne Ward, Sunil Issar
NAACL
1994
13 years 4 months ago
Phonological Parsing for Bi-directional Letter-to-Sound/Sound-to-Letter Generation
In this paper, we describe a reversibleletter-to-sound/soundto-letter generation system based on an approach which combines a rule-based formalism with data-driven techniques. We ...
Helen M. Meng, Stephanie Seneff, Victor Zue
NAACL
1994
13 years 4 months ago
On-Line Cursive Handwriting Recognition Using Hidden Markov Models and Statistical Grammars
The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuou...
John Makhoul, Thad Starner, Richard M. Schwartz, G...
NAACL
1994
13 years 4 months ago
Session 13: CSR Search
This session had five papers related to different topics in CSR Search. The topics ranged from integration of many knowledge sources within a practical system, to different search...
Richard M. Schwartz
NAACL
1994
13 years 4 months ago
Integrated Text and Image Understanding for Document Understanding
Because of the complexity of documents and the variety of applications which must be supported, document understanding requires the integration of image understanding with text un...
Suzanne Liebowitz Taylor, Deborah A. Dahl, Mark Li...
NAACL
1994
13 years 4 months ago
Language Identification via Large Vocabulary Speaker Independent Continuous Speech Recognition
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the...
Steve Lowe, Anne Demedts, Larry Gillick, Mark Mand...
NAACL
1994
13 years 4 months ago
Semantic Evaluation for Spoken-Language Systems
Development has begun on a semantic evaluation (SemEval) methodology and infrastructure for the ARPA Spoken Language Program. SemEval is an attempt to define a task-independent te...
Robert C. Moore
NAACL
1994
13 years 4 months ago
Language Modeling with Sentence-Level Mixtures
Thispaperintroduces a simple mixtare languagemodelthat attempts to capture long distance conslraints in a sentence orparagraph. The model is an m-component mixture of Irigram mode...
Rukmini Iyer, Mari Ostendorf, Jan Robin Rohlicek