SRI International
-
Promising approaches to broadening youth participation in STEM
The National Science Foundation (NSF) views broadening participation in the nation’s STEM enterprise as vitally linked to the United States’ capacity for innovation.
-
Improving the Robustness of Team Collaboration through Analysis of Qualitative Interactions
We introduce coordination rules that facilitate collaboration between autonomous agents when communication is lost.
-
Can Adaptive Courseware Technology Positively Impact Student Learning Outcomes?
In higher education, if students fail to successfully complete the courses offered in the first few terms of school, they can jeopardize their dreams of a college degree. In two-year colleges, the courses representing the greatest hurdles are often developmental courses in English or math. In four-year colleges, they often are introductory courses in subjects…
-
New Report Highlights Key Findings from Next Generation STEM Schools Forum
In the 2015 State of the Union address, President Obama called for Next Generation High Schools. Next Generation STEM schools seek to intensify Science, Technology, Engineering and Math (STEM) opportunities, especially for historically underrepresented students. Such schools aim to strengthen STEM learning for all students who have a strong interest in STEM, regardless of their…
-
Exploring the role of phonetic bottleneck features for speaker and language recognition
Using bottleneck features extracted from a deep neural network (DNN) trained to predict senone posteriors has resulted in new, state-of-the-art technology for language and speaker identification.
-
Noise and reverberation effects on depression detection from speech
This study compares the effect of noise and reverberation on depression prediction using standard mel-frequency cepstral coefficients, and features designed for noise robustness, damped oscillator cepstral coefficients.
-
Analyzing the effect of channel mismatch on the SRI language recognition evaluation 2015 system
We present the work done by our group for the 2015 language recognition evaluation (LRE) organized by the National Institute of Standards and Technology (NIST).
-
Spoken Interaction Modeling for Automatic Assessment of Collaborative Learning
This study investigates whether automatic audio- based monitoring of interactions can predict collaboration quality.
-
Extending Semantically Enabled Virtual Environments for Training Assessment
This paper reports the lessons learned from several recent research and development projects, and offers some directions for new studies that build on this work.
-
A Phonetically Aware System for Speech Activity Detection
In this paper, we focus on a dataset of highly degraded signals, developed under the DARPA Robust Automatic Transcription of Speech (RATS) program.
-
Playing the Long Game: Utah Renews Investment in its Innovation Ecosystem
Innovation—the process of creating new products and services and delivering them to customers—is tough. It’s tough, because the innovation process is nonlinear, requires adaptation, requires multiple skillsets, and engaging multiple stakeholders. Regions with strong innovation systems are well known, but where do states trying to build innovation systems start? Utah offers some good lessons. In…
-
Additive Manufacturing: Re-thinking Battery Design
In this article we focus on recent advances in additive manufacturing for batteries and highlight current and future research directions for battery design, manufacturing, and integration for small, portable and wearable electronics.