Sciweavers

1084 search results - page 59 / 217
» Hidden Markov Models with Multiple Observation Processes
Sort
View
ICASSP
2010
IEEE
15 years 1 days ago
Framework for cross-language automatic phonetic segmentation
Annotation of large multilingual corpora remains a challenge to the data-driven approach to speech research, especially for under-resourced languages. This paper presents crosslan...
Udochukwu Kalu Ogbureke, Julie Carson-Berndsen
ICASSP
2009
IEEE
15 years 6 months ago
A variational EM algorithm for learning eigenvoice parameters in mixed signals
We derive an efficient learning algorithm for model-based source separation for use on single channel speech mixtures where the precise source characteristics are not known a pri...
Ron J. Weiss, Daniel P. W. Ellis
ICMLA
2004
15 years 1 months ago
Planning with predictive state representations
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to traditional models such as partially observable Mark...
Michael R. James, Satinder P. Singh, Michael L. Li...
ICIAP
2009
ACM
16 years 13 days ago
A New Generative Feature Set Based on Entropy Distance for Discriminative Classification
Abstract. Score functions induced by generative models extract fixeddimensions feature vectors from different-length data observations by subsuming the process of data generation, ...
Alessandro Perina, Marco Cristani, Umberto Castell...
EMNLP
2007
15 years 1 months ago
Bootstrapping Information Extraction from Field Books
We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
Sander Canisius, Caroline Sporleder