Publications
-
Fisheye Word Cloud for temporal sentiment exploration
This poster abstract presents a new word cloud technique, the Fisheye Word Cloud, for exploring time-series data in a focused+context approach to analyzing word data.
-
“Can You Give Me Another Word for Hyperbaric?”: Improving Speech Translation Using Targeted Clarification Questions
We present a novel approach for improving communication success between users of speech-to-speech translation systems by automatically detecting errors in the output of automatic speech recognition (ASR) and statistical machine…
-
Characteristics of an Advanced Carbon Sorbent for CO2 Capture
The adsorption and desorption characteristics on an advanced carbon sorbent for gases present in the flue gas stream, including CO2, N2, O2, Ar, H2O vapor, and impurities NO and SO2 are…
-
N-Gram Extension for Bag-of-Audio-Words
With ... enhanced representation, we find the average probability of miss noticeably decreases when evaluated on TRECVID 2011 and 2012 datasets, indicating clear improvements on the multimedia event detection task.
-
Activation of Heme Biosynthesis by a Small Molecule That Is Toxic to Fermenting Staphylococcus Aureus
Here, we describe the identification of a small molecule activator of HssRS that induces endogenous heme biosynthesis by perturbing central metabolism.
-
Are All Types of Internet Voting Unsafe?
IEEE, like many other professional organizations, uses a third-party vendor to conduct elections over the Internet to elect its leaders.
-
Improving Speaker Identification Robustness to Highly Channel-Degraded Speech Through Multiple System Fusion
This article describes our submission to the speaker identification (SID) evaluation for the first phase of the DARPA Robust Audio and Transcription of Speech (RATS) program.
-
Modulation of Limbic-Cerebellar Functional Connectivity Enables Alcoholics to Recognize Who Is Who
Using an fMRI paradigm, we investigated whether memory performance by alcoholics on a face–name association test previously observed to be problematic for alcoholics could be explained by desynchronous activity between…
-
Articulatory trajectories for large-vocabulary speech recognition
We present a neural network model to estimate articulatory trajectories from speech signals where the model was trained using synthetic speech signals generated by Haskins Laboratories’ task-dynamic model of speech…
-
SRI Submissions to Chinese-English PatentMT NTCIR10 Evaluation
The SRI team submitted translation results using a combined output from two types of grammars supported in SRlnterp, with two different word segmentations.
-
Using multiple versions of speech input in phone recognition
This study investigates the use of multiple versions of the same speech unit in automatic phone recognition.
-
Discovering the Determinants of Diversity in the Human NK Cell Repertoire by Mass Cytometry
To provide a framework for understanding how perturbations in expression of NKRs influence disease pathogenesis, we defined the phenotypic heterogeneity of NK cells in 22 healthy individuals (ages 21-62; M=10,…