Sciweavers

376 search results - page 71 / 76
» Analysis-by-synthesis features for speech recognition
Sort
View
GECCO
2006
Springer
169views Optimization» more  GECCO 2006»
13 years 10 months ago
An open-set speaker identification system using genetic learning classifier system
This paper presents the design and implementation of an adaptive open-set speaker identification system with genetic learning classifier systems. One of the challenging problems i...
WonKyung Park, Jae C. Oh, Misty K. Blowers, Matt B...
DIAGRAMS
2008
Springer
13 years 8 months ago
Diagrammatic Logic of Existential Graphs: A Case Study of Commands
Diagrammatic logics have advantages over symbolic cousins. Peirce thought that logical diagrams (Existential Graphs, EG) are capable of "expression of all assertions", as...
Ahti-Veikko Pietarinen
NAACL
2003
13 years 8 months ago
Factored Language Models and Generalized Parallel Backoff
We introduce factored language models (FLMs) and generalized parallel backoff (GPB). An FLM represents words as bundles of features (e.g., morphological classes, stems, data-drive...
Jeff Bilmes, Katrin Kirchhoff
ICASSP
2010
IEEE
13 years 6 months ago
Semantic confidence calibration for spoken dialog applications
The success of spoken dialog applications depends strongly on the quality of the semantic confidence measure that determines the selection of the dialog strategy. However, the sem...
Dong Yu, Li Deng
CSL
2010
Springer
13 years 6 months ago
Improving supervised learning for meeting summarization using sampling and regression
Meeting summarization provides a concise and informative summary for the lengthy meetings and is an effective tool for efficient information access. In this paper, we focus on ext...
Shasha Xie, Yang Liu