Author: SRI International
-
Semiconductor defect engineering – materials, synthetic structures and devices
This book explores the deliberate introduction and manipulation of defects and impurities for the purpose of engineering desired properties in semiconductor materials and devices.
-
Working a call: multiparty management and interactional infrastructure in calls for help
-
Optical gain from InAs nanocystal quantum dots in polymer matrix
We report on the observation of optical gain from InAs nanocrystal quantum dots which emit at 1.55microns and are imbedded in a novel polymer platform.
-
AAAI: it’s time for large-scale systems
The most important challenge facing AI today is enabling components to interact in larger scale systems, where modules built with multiple alternative methodologies can be incorporated into robust applications.
-
Segmentation of Aerial Surveillance Video Using a Mixture of Experts
We propose a video segmentation algorithm for aerial surveillance video. The algorithm uses a Mixture of Experts consisting of a supervised image segmentation algorithm named the Trainable Sequential MAP segmentation algorithm.
-
Thirty-Six-Month Outcomes for Families of Children Who Have Disabilities and Participated in Early Intervention
Results suggest that Part C early intervention provides important supports for families of young children with disabilities. The findings reinforce the need for experimental research to identify factors that are most likely to lead to successful outcomes for all families.
-
The Status of the Teaching Profession 2005
This annual report provides an update on California’s teacher development and teacher quality policies; discusses trends in the supply of and demand for teachers; examines data on novice, underprepared, out of field teachers; and investigates the local policies and decisions that influence the maldistribution of teachers.
-
Incorporating Tandem / HATs MLP Features into SRI’s Conversational Speech Recognition System
We describe the development of a speech recognition system for conversational telephone speech (CTS) that incorporates acoustic features estimated by multilayer perceptrons (MLPs). The acoustic features are based on frame-level phone posterior probabilities, obtained by merging two different MLP estimators, one based on PLP-Tandem features, the other based on hidden activation TRAPs (HATs) features.
-
Multirate ASR Models for Phone-Class Dependent N-Best List Rescoring
In this work, we describe a technique to augment a recognizer that uses this compromise with information from multiple-rate spectral models that emphasize either better time or better frequency resolution in order to improve performance.
-
A* Based Joint Segmentation and Classification of Dialog Acts in Multiparty Meetings
We investigate the use of the A* algorithm for joint segmentation and classification of dialog acts (DAs) of the ICSI Meeting Corpus. The proposed method is evaluated on both traditional and new metrics, and compared with our previous work on the same task.
-
Constructing Padi Measurement Models for the BEAR Scoring Engine (Padi Technical Report 7)
Connections among the task design, student work products, evaluation, and inferential reasoning are highlighted, and the BEAR Scoring Engine is presented as one example of how multidimensional item response modeling can be integrated with the PADI design system
-
Four Weightings and a Fusion: A Cepstral-SVM System for Speaker Recognition
A new speaker recognition system is described that uses Mel-frequency cepstral features. This system is a combination of four support vector machines (SVMs). All the SVM systems use polynomial features and they are trained and tested independently using a linear inner-product kernel.