Publications
-
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…
-
Development of Phrase Translation Systems for Handheld Computers: from Concept to Field
We describe the development and conceptual evolution of handheld spoken phrase translation systems, beginning with an initial undirectional system for translation of English phrases, and later extending to a limited…
-
Spatial Temporal and Histogram Video Registration for Digital Watermark Detection
In this paper, we propose a spatial, temporal and histogram (STH) registration algorithm for video sequences. This algorithm is developed based on a frame-level model of the misalignments often introduced…