Sciweavers

NAACL
2007
13 years 5 months ago
A Geometric Interpretation of Non-Target-Normalized Maximum Cross-Channel Correlation for Vocal Activity Detection in Meetings
Vocal activity detection is an important technology for both automatic speech recognition and automatic speech understanding. In meetings, standard vocal activity detection algori...
Kornel Laskowski, Tanja Schultz
NAACL
2007
13 years 5 months ago
Virtual Evidence for Training Speech Recognizers Using Partially Labeled Data
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...
Amarnag Subramanya, Jeff A. Bilmes
NAACL
2007
13 years 5 months ago
Comparing User Simulation Models For Dialog Strategy Learning
This paper explores what kind of user simulation model is suitable for developing a training corpus for using Markov Decision Processes (MDPs) to automatically learn dialog strate...
Hua Ai, Joel R. Tetreault, Diane J. Litman
NAACL
2007
13 years 5 months ago
Are Some Speech Recognition Errors Easier to Detect than Others?
This study investigates whether some speech recognition (SR) errors are easier to detect and what patterns can be identified from those errors. Specifically, SR errors were exam...
Yongmei Shi, Lina Zhou
NAACL
2007
13 years 5 months ago
Translation Model Pruning via Usage Statistics for Statistical Machine Translation
We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system ...
Matthias Eck, Stephan Vogel, Alex Waibel
NAACL
2007
13 years 5 months ago
Joint Morphological-Lexical Language Modeling for Machine Translation
We present a joint morphological-lexical language model (JMLLM) for use in statistical machine translation (SMT) of language pairs where one or both of the languages are morpholog...
Ruhi Sarikaya, Yonggang Deng
NAACL
2007
13 years 5 months ago
Situated Models of Meaning for Sports Video Retrieval
Situated models of meaning ground words in the non-linguistic context, or situation, to which they refer. Applying such models to sports video retrieval requires learning appropri...
Michael Fleischman, Deb Roy
NAACL
2007
13 years 5 months ago
Joint Versus Independent Phonological Feature Models within CRF Phone Recognition
We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved ...
Ilana Bromberg, Jeremy Morris, Eric Fosler-Lussier