SRI International
-
Reliability of Adult Retrospective Recall of Lifetime Tobacco Use
The present analyses examined the test–retest reliability of retrospective tobacco use measures, including details of first use, circumstances of first use, and initial subjective reactions.
-
Speech Recognition as Feature Extraction for Speaker Recognition
We present specific techniques and results from SRI’s NIST speaker recognition evaluation system.
-
Studying how mobile computing with tablet PCs supports school and classroom changes in Singapore
-
Towards Live Informing and Automatic Analyzing of Student Learning: Reporting in the Assistment System
In this article we describe the types of reports that we have designed and implemented that provide real time reporting to teachers in their classrooms. Experiment analysis tools are available to facilitate researchers to carry out randomized controlled learning experiments so that they are able to compare different tutoring strategies.
-
Parameterization of Prosodic Feature Distributions for SVM Modeling in Speaker Recognition
This paper explores the important question of finding a good kernel for a system that models syllable-based prosodic features using support vector machines (SVMs). We introduce two new methods for transforming the syllable-level features into a single high-dimensional vector that can be well modeled by SVMs, resulting in significant gains in speaker recognition performance.
-
Precise Visual Navigation Using Multi-Stereo Vision and Landmark Matching
In this paper, we propose a set of techniques which greatly reduce the long term drift and also improve its robustness to many failure conditions.
-
Caregiver Descriptions of the Developmental Skills of Infants and Toddlers Entering Early Intervention Services
The present study was conducted to describe the developmental skills of a national sample of infants and toddlers at entry into early intervention services.
-
Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition
This paper uses a state-of-the-art Mandarin recognition system as a platform to study the interaction of three techniques. Experiments in the broadcast news and broadcast conversation domains show that the contribution of each technique is nonredundant.
-
High carrier mobility polythiophene thin films: structure determination by experiment and theory
The structure within crystalline thin films of a high-carrier-mobility polythiophene is studied with complementary characterization methods and first-principles theory.
-
Deflation-secure web metering
We introduce the first protocols for audience metering that protect against deflation attempts by CDs.
-
Balancing push and pull for efficient information discovery in large-scale sensor networks
Abstract In this paper, we investigate efficient strategies for supporting on-demand information dissemination and gathering in large-scale wireless sensor networks. In particular, we propose a “comb-needle” discovery support model resembling an ancient method: use a comb to help find a needle in sand or a haystack. The model combines push and pull for information dissemination…
-
Proactivity in an Intentionally Helpful Personal Assistive Agent
This position paper outlines some initial thoughts on desired forms of proactive behavior, and identifies technical challenges in developing systems that embody such behaviors.