Author: SRI International
-
Building a Highly Accurate Mandarin Speech Recognizer with Language-Independent Technologies and Language-Dependent Modules
We describe a system for highly accurate large-vocabulary Mandarin speech recognition. The prevailing hidden Markov model based technologies are essentially language independent and constitute the backbone of our system.
-
Effect of Various Coal Contaminants on the Performance of Solid Oxide Fuel Cells: Part I. Accelerated Testing
The contaminants that are potentially present in the coal-derived gas stream and their thermochemical nature are discussed.
-
Multiple-Target Tracking Via Kinematics, Shape, and Appearance-Based Data Association
This paper presents a real time system for tracking multiple ground moving targets in aerial video.
-
The Wake-Promoting Effects of Hypocretin-1 are Attenuated in Old Rats
We sought to determine whether the wake-promoting effect of hypocretin changes with age in Wistar rats, a strain in which age-related changes in both sleep and hypocretin signaling have been reported.
-
Effect of Various Coal Contaminants on the Performance of Solid Oxide Fuel Cells: Part II. Ppm and Sub-Ppm Level Testing
The poisoning effects of various trace contaminants in the coal-derived syngas stream at ppm and sub-ppm level on the performance of Ni-YSZ/YSZ/LSM solid oxide fuel cells were studied at extended duration.
-
Fundamental Performance Differences Between CMOS and COD Imagers: Part III
This paper is a status report on recent scientific CMOS imager developments since when previous publications were written.
-
Comparison of the Antinociceptive and Antirewarding Profiles of Novel Bifunctional Nociceptin Receptor/Mu-Opioid Receptor Ligands: Implications for Therapeutic Applications
We hypothesized that NOPr agonists, with bifunctional activity at the μ-opioid receptor (MOPr), may function as nonaddicting analgesics or as drug abuse medications.
-
Modeling other talkers for improved dialog act recognition in meetings
We propose a new approach that takes into account speech from other talkers, relying only on speech/non-speech information from all participants.
-
An anticorrelation kernel for subsystem training in multiple classifier systems
We present a method for training support vector machine (SVM)-based classification systems for combination with other classification systems designed for the same task.
-
Development of the 2008 SRI Mandarin Speech-To-Text System for Broadcast News and Conversation
We describe the recent progress in SRI’s Mandarin speech-to-text system developed for 2008 evaluation in the DARPA GALE program. A data-driven lexicon expansion technique and language model adaptation methods contribute to the improvement in recognition performance.
-
Measurements of OH and HO2 Concentrations During the MCMA-2006 Field Campaign – Part 2: Model Comparison and Radical Budget
Measurements of hydroxyl and hydroperoxy radicals were made during the Mexico City Metropolitan Area field campaign as part of the MILAGRO project during March 2006.
-
Multicamera Tracking of Articulated Human Motion Using Shape and Motion Cues
We present a completely automatic algorithm for initializing and tracking the articulated motion of humans using image sequences obtained from multiple cameras.