Sciweavers

577 search results - page 76 / 116
» Improved Text Generation Using N-gram Statistics
Sort
View
ICMCS
2000
IEEE
122views Multimedia» more  ICMCS 2000»
14 years 2 months ago
Translingual Visual Speech Synthesis
—This paper describes a morphing-based audio driven facial animation system. Based on an incoming audio stream, a face image is animated with full lip synchronization and synthes...
Tanveer A. Faruquie, Chalapathy Neti, Nitendra Raj...
IPM
2008
102views more  IPM 2008»
13 years 10 months ago
Fast exact maximum likelihood estimation for mixture of language model
Language modeling is an effective and theoretically attractive probabilistic framework for text information retrieval. The basic idea of this approach is to estimate a language mo...
Yi Zhang 0001, Wei Xu
ICPR
2008
IEEE
14 years 11 months ago
Semi-supervised learning on large complex simulations
Complex simulations can generate very large amounts of data stored disjointly across many local disks. Learning from this data can be problematic due to the difficulty of obtainin...
John Nicholas Korecki, Kevin W. Bowyer, Larry O. H...
ICASSP
2009
IEEE
14 years 4 months ago
Trajectory training considering global variance for HMM-based speech synthesis
This paper presents a novel method for training hidden Markov models (HMMs) for use in HMM-based speech synthesis. The primary goal of HMM parameter optimization is to ensure that...
Tomoki Toda, Steve Young
ICDE
2007
IEEE
182views Database» more  ICDE 2007»
14 years 11 months ago
Discriminative Frequent Pattern Analysis for Effective Classification
The application of frequent patterns in classification appeared in sporadic studies and achieved initial success in the classification of relational data, text documents and graph...
Hong Cheng, Xifeng Yan, Jiawei Han, Chih-Wei Hsu