Publications
-
MUESLI: Multiple utterance error correction for a spoken language interface
We propose a method for using all available information to help correct recognition errors in tasks that use constrained grammars of the kind used in the domain of Command and…
-
Strategies for building a Farsi-English SMT system from limited resources
In this paper we will focus on the kinds of improvements for a Farsi-to- English translation system achieved by means of algorithmic changes, adding raw, domain-unspecific resources, and unsupervised morphological…
-
The case for automatic higher-level features in forensic speaker recognition
We provide an overview of automatic higher-level systems and discuss potential advantages, as well as issues, for their use in the forensic context.
-
Development of SRI’s translation systems for broadcast news and broadcast conversations
We present our recent work on developing large-vocabulary Arabic-to-English and Chinese-to-English speech-to-text translation systems for the January 2008 Global Autonomous Language Exploitation (GALE) retest evaluation.
-
Is Alignment Enough? Investigating the Effects of State Policies and Professional Development on Science Curriculum Implementation
This paper focuses on teachers’ perceptions of curricular alignment and on curriculum implementation using empirical data from a statewide systemic inquiry science reform effort targeting students from kindergarten to eighth…
-
Modeling prior belief for speaker verification SVM systems
In this paper we propose to relax the assumption that the covariance matrix is the identity matrix, allowing it to be a more general block diagonal matrix. We show results…
-
Fast Color/Texture Segmentation for Outdoor Robots
We present results of applying our descriptor for segmenting a synthetic image and compare it against other state-of-the-art descriptors.
-
Translational Studies of Alcoholism: Bridging the Gap
Together, studies in humans and animal models have provided support for the involvement of specific brain structures over the course of alcohol addiction.
-
Weakly Supervised Training for Parsing Mandarin Broadcast Transcripts
We compare co-training to self-training, and our results show that performance using co-training is significantly better than with self-training and both co-training and self-training with a small seed labeled corpus…
-
Development of the SRI/Nightingale Arabic ASR System
We describe the large vocabulary automatic speech recognition system developed for Modern Standard Arabic used for the 2007 GALE evaluation as part of the speech translation system.
-
Gene Expression Analysis Reveals New Possible Mechanism of Vancomycin-Induced Nephrotoxicity and Identifies Gene Markers Candidates
The goals of this study were to gain insights into molecular mechanisms of nephrotoxicity at the genomic level, evaluate gene markers of vancomycin-induced kidney injury, and compare gene expression responses…
-
Logical Hierarchical Hidden Markov Models for Modeling User Activities
In this work we develop a representation that naturally combines the power of both relational and hierarchical models in the form of Logical Hierarchical Hidden Markov Models (LoHiHMMs).