Publications
-
Project Halo: Towards a Digital Aristotle
Project Halo is a multi-staged effort, sponsored by Vulcan Inc, aimed at creating the Digital Aristotle, an application that will encompass much of the world's scientific knowledge and be capable…
-
National Early Intervention Longitudinal Study: Demographic Characteristics of Children and Families Entering Early Intervention. NEILS Data Report No. 3
The National Early Intervention Longitudinal Study (NEILS) is being conducted to address some of the most important questions related to the implementation and outcomes of Part C of the Individuals…
-
The Relationship Between Dialogue Acts and Hot Spots in Meetings
We examine the relationship between hot spots and dialogue acts in roughly 32 hours of speech data from naturally-occurring meetings. Results reveal that four independently-motivated involvement categories (non-involved, disagreeing, amused,…
-
Speaker Recognition using Prosodic and Lexical Features
We investigate the contribution of modeling prosodic and lexical patterns, on performance in the NIST 2003 Speaker Recognition Evaluation extended data task.
-
UpLib: a universal personal digital library system
We describe the design and use of a personal digital library system, UpLib.
-
UpLib: a universal personal digital library system
We describe the design and use of a personal digital library system, UpLib.
-
RegReg: a Lightweight Generator of Robust Parsers for Irregular Languages
We present a lightweight tool, called RegReg, based on a hierarchy of lexers described by tagged regular expressions. By using tags, the automatically generated parse tree can be easily manipulated.
-
Leverage Points For Improving Educational Assessment (Padi Technical Report 2)
This presentation first reviews an evidence-centered framework for designing and analyzing assessments. It then uses this framework to discuss and to illustrate how advances in technology, education, and psychology can…
-
Spotting “Hot Spots” in Meetings: Human Judgments and Prosodic Cues
Recent interest in the automatic processing of meetings is motivated by a desire to summarize, browse, and retrieve important information from lengthy archives of spoken data. One of the most…
-
Unlocking the Learning Value of Wireless Mobile Devices
Many researchers see the potential of wireless mobile learning devices to achieve large-scale impact on learning because of portability, low cost, and communications features.
-
Modeling Duration Patterns for Speaker Recognition
We present a method for speaker recognition that uses the duration patterns of speech units to aid speaker classification. The approach represents each word and/or phone by a feature vector…
-
Automatic Disfluency Identification in Conversational Speech Using Multiple Knowledge Sources
This work investigates a number of knowledge sources for disfluency detection, including acoustic-prosodic features, a language model (LM) to account for repetition patterns, a part-of-speech (POS) based LM, and rule-based…