Regularized Urdu Speech Recognition with Semi-Supervised Deep Learning
Applied Sciences, 2019 Automatic Speech Recognition, (ASR) has achieved the best results for English, with end-to-end neural network based supervised models. These supervised models need huge amounts of labeled speech data for good generalization, which can be quite a ...
Mohammad Ali Humayun +6 more
doaj +1 more source
Generalized Species Sampling Priors with Latent Beta reinforcements
, 2014 Many popular Bayesian nonparametric priors can be characterized in terms of exchangeable species sampling sequences. However, in some applications, exchangeability may not be appropriate. We introduce a {novel and probabilistically coherent family of non-
Blei D. +16 more
core +2 more sources
Properties of the Statistical Complexity Functional and Partially Deterministic HMMs
Entropy, 2009 Statistical complexity is a measure of complexity of discrete-time stationary stochastic processes, which has many applications. We investigate its more abstract properties as a non-linear function of the space of processes and show its close relation to
Wolfgang Löhr
doaj +1 more source
Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Models
, 2018 Generalizing manipulation skills to new situations requires extracting invariant patterns from demonstrations. For example, the robot needs to understand the demonstrations at a higher level while being invariant to the appearance of the objects ...
Calinon, Sylvain +7 more
core
Propositionalisation of multiple sequence alignments using probabilistic models [PDF]
, 2008 Multiple sequence alignments play a central role in Bioinformatics. Most alignment representations are designed to facilitate knowledge extraction by human experts.
Holmes, Geoffrey +2 more
core +2 more sources
Duration and Interval Hidden Markov Model for Sequential Data Analysis
, 2015 Analysis of sequential event data has been recognized as one of the essential tools in data modeling and analysis field. In this paper, after the examination of its technical requirements and issues to model complex but practical situation, we propose a ...
Kasai, Hiroyuki, Narimatsu, Hiromi
core +1 more source
Solution to error source model selection problem in IS EASECC
Advanced Engineering Research, 2017 Introduction. The development of error-correcting techniques in digital transmission channels is considered. This is a multiparameter problem the solution of which through the analytical methods is rather difficult.
Vladimir M Deundyak +2 more
doaj +1 more source
A cross-center smoothness prior for variational Bayesian brain tissue segmentation
, 2019 Suppose one is faced with the challenge of tissue segmentation in MR images, without annotators at their center to provide labeled training data. One option is to go to another medical center for a trained classifier.
A Opbroek Van +18 more
core +1 more source
SynSys: A Synthetic Data Generation System for Healthcare Applications
Sensors, 2019 Creation of realistic synthetic behavior-based sensor data is an important aspect of testing machine learning techniques for healthcare applications. Many of the existing approaches for generating synthetic data are often limited in terms of complexity ...
Jessamyn Dahmen, Diane Cook
doaj +1 more source
Inference in Hidden Markov Models with Explicit State Duration Distributions
, 2012 In this letter we borrow from the inference techniques developed for unbounded state-cardinality (nonparametric) variants of the HMM and use them to develop a tuning-parameter free, black-box inference procedure for Explicit-state-duration hidden Markov ...
Dewar, Michael +2 more
core +2 more sources