Sciweavers

1209 search results - page 21 / 242
» Using Prosodic Features in Language Models for Meetings
Sort
View
108
Voted
UAI
2008
15 years 4 months ago
Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression
Although fully generative models have been successfully used to model the contents of text documents, they are often awkward to apply to combinations of text data and document met...
David M. Mimno, Andrew McCallum
164
Voted
NAACL
2004
15 years 4 months ago
Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness ...
Joungbum Kim, Sarah E. Schwarm, Mari Ostendorf
117
Voted
DISCEX
2003
IEEE
15 years 8 months ago
MuCAPSL
Secure group communication protocols have been designed to meet needs such as secure management of group membership, confidential group communication, and access control. New lan...
Jonathan K. Millen, Grit Denker
120
Voted
ECBS
2003
IEEE
105views Hardware» more  ECBS 2003»
15 years 8 months ago
Panel: Extending UML from Software to Systems Engineering
“The Unified Modeling Language (UML) is a graphical language for visualizing, specifying, constructing, and documenting the artifacts of a softwareintensive system” [1]. This ...
Stephanie White, Murray Cantor, Sanford Friedentha...
124
Voted
CLEAR
2007
Springer
148views Biometrics» more  CLEAR 2007»
15 years 9 months ago
Multi-stage Speaker Diarization for Conference and Lecture Meetings
The LIMSI RT-07S speaker diarization system for the conference and lecture meetings is presented in this paper. This system builds upon the RT06S diarization system designed for le...
Xuan Zhu, Claude Barras, Lori Lamel, Jean-Luc Gauv...