996 resultados para Nicolás Factor Beato, 1520-1583-Biografies


Relevância:

30.00% 30.00%

Publicador:

Resumo:

Model based compensation schemes are a powerful approach for noise robust speech recognition. Recently there have been a number of investigations into adaptive training, and estimating the noise models used for model adaptation. This paper examines the use of EM-based schemes for both canonical models and noise estimation, including discriminative adaptive training. One issue that arises when estimating the noise model is a mismatch between the noise estimation approximation and final model compensation scheme. This paper proposes FA-style compensation where this mismatch is eliminated, though at the expense of a sensitivity to the initial noise estimates. EM-based discriminative adaptive training is evaluated on in-car and Aurora4 tasks. FA-style compensation is then evaluated in an incremental mode on the in-car task. © 2011 IEEE.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Vector Taylor Series (VTS) model based compensation is a powerful approach for noise robust speech recognition. An important extension to this approach is VTS adaptive training (VAT), which allows canonical models to be estimated on diverse noise-degraded training data. These canonical model can be estimated using EM-based approaches, allowing simple extensions to discriminative VAT (DVAT). However to ensure a diagonal corrupted speech covariance matrix the Jacobian (loading matrix) relating the noise and clean speech is diagonalised. In this work an approach for yielding optimal diagonal loading matrices based on minimising the expected KL-divergence between the diagonal loading matrix and "correct" distributions is proposed. The performance of DVAT using the standard and optimal diagonalisation was evaluated on both in-car collected data and the Aurora4 task. © 2012 IEEE.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Rationale: Increasing epithelial repair and regeneration may hasten resolution of lung injury in patients with the Acute Respiratory Distress Syndrome (ARDS). In animal models of ARDS, Keratinocyte Growth Factor (KGF) reduces injury and increases epithelial proliferation and repair. The effect of KGF in the human alveolus is unknown.

Objectives: To test whether KGF can attenuate alveolar injury in a human model of ARDS.

Methods: Volunteers were randomized to intravenous KGF (60 μg/kg) or placebo for 3 days, before inhaling 50μg lipopolysaccharide. Six hours later, subjects underwent bronchoalveolar lavage (BAL) to quantify markers of alveolar inflammation and cell-specific injury.

Measurements and Main Results: KGF did not alter leukocyte infiltration or markers of permeability in response to LPS. KGF increased BAL concentrations of Surfactant Protein D (SP-D), MMP-9, IL-1Ra, GM-CSF and CRP. In vitro, BAL fluid from KGF-treated subjects (KGF BAL) inhibited pulmonary fibroblast proliferation, but increased alveolar epithelial proliferation. Active MMP-9 increased alveolar epithelial wound repair. Finally, BAL from the KGF pre-treated group enhanced macrophage phagocytic uptake of apoptotic epithelial cells and bacteria compared with BAL from the placebo-treated group. This effect was blocked by inhibiting activation of the GM-CSF receptor.

Conclusions: KGF treatment increases BAL SP-D, a marker of type II alveolar epithelial cell proliferation in a human model of ALI. Additionally KGF increases alveolar concentrations of the anti-inflammatory cytokine IL-1Ra, and mediators that drive epithelial repair (MMP-9) and enhance macrophage clearance of dead cells and bacteria (GM-CSF).