@article{6075,
  abstract     = {{For almost three decades, the theory of visual attention (TVA) has been successful in mathematically describing and explaining a wide variety of phenomena in visual selection and recognition with high quantitative precision. Interestingly, the influence of feature contrast on attention has been included in TVA only recently, although it has been extensively studied outside the TVA framework. The present approach further develops this extension of TVA’s scope by measuring and modeling salience. An empirical measure of salience is achieved by linking different (orientation and luminance) contrasts to a TVA parameter. In the modeling part, the function relating feature contrasts to salience is described mathematically and tested against alternatives by Bayesian model comparison. This model comparison reveals that the power function is an appropriate model of salience growth in the dimensions of orientation and luminance contrast. Furthermore, if contrasts from the two dimensions are comb}},
  author       = {{Krüger, Alexander and Tünnermann, Jan and Scharlau, Ingrid}},
  issn         = {{1943-3921}},
  journal      = {{Attention, Perception, & Psychophysics}},
  keywords     = {{Salience, Visual attention, Bayesian inference, Theory of visual attention, Computational modeling, Inference, Object Recognition, Theories, Visual Perception, Visual Attention, Luminance, Perceptual Orientation, Statistical Probability, Stimulus Salience, Computational Modeling}},
  number       = {{6}},
  pages        = {{1593 -- 1614}},
  title        = {{{Measuring and modeling salience with the theory of visual attention.}}},
  doi          = {{10.3758/s13414-017-1325-6}},
  volume       = {{79}},
  year         = {{2017}},
}

@article{6071,
  abstract     = {{Particular differences between an object and its surrounding cause salience, guide attention, and improve performance in various tasks. While much research has been dedicated to identifying which feature dimensions contribute to salience, much less regard has been paid to the quantitative strength of the salience caused by feature differences. Only a few studies systematically related salience effects to a common salience measure, and they are partly outdated in the light of new findings on the time course of salience effects. We propose Bundesen’s Theory of Visual Attention (TV A) as a theoretical basis for measuring salience and introduce an empirical and modeling approach to link this theory to data retrieved from temporal-order judgments. With this procedure, TV A becomes applicable to a broad range of salience-related stimulus material. Three experiments with orientation pop-out displays demonstrate the feasibility of the method. A 4th experiment substantiates its applicability t}},
  author       = {{Krüger, Alexander and Tünnermann, Jan and Scharlau, Ingrid}},
  issn         = {{1895-1171}},
  journal      = {{Advances in Cognitive Psychology}},
  keywords     = {{salience, visual attention, Bayesian inference, theory of visual attention, computational modeling, Visual Attention, Computational Modeling, Inference, Judgment, Statistical Probability}},
  number       = {{1}},
  pages        = {{20 -- 38}},
  title        = {{{Fast and conspicuous? Quantifying salience with the theory of visual attention.}}},
  doi          = {{10.5709/acp-0184-1}},
  volume       = {{12}},
  year         = {{2016}},
}

@article{11846,
  abstract     = {{In this paper, we present a new technique for automatic speech recognition (ASR) in reverberant environments. Our approach is aimed at the enhancement of the logarithmic Mel power spectrum, which is computed at an intermediate stage to obtain the widely used Mel frequency cepstral coefficients (MFCCs). Given the reverberant logarithmic Mel power spectral coefficients (LMPSCs), a minimum mean square error estimate of the clean LMPSCs is computed by carrying out Bayesian inference. We employ switching linear dynamical models as an a priori model for the dynamics of the clean LMPSCs. Further, we derive a stochastic observation model which relates the clean to the reverberant LMPSCs through a simplified model of the room impulse response (RIR). This model requires only two parameters, namely RIR energy and reverberation time, which can be estimated from the captured microphone signal. The performance of the proposed enhancement technique is studied on the AURORA5 database and compared to that of constrained maximum-likelihood linear regression (CMLLR). It is shown by experimental results that our approach significantly outperforms CMLLR and that up to 80\% of the errors caused by the reverberation are recovered. In addition to the fact that the approach is compatible with the standard MFCC feature vectors, it leaves the ASR back-end unchanged. It is of moderate computational complexity and suitable for real time applications.}},
  author       = {{Krueger, Alexander and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{ASR, AURORA5 database, automatic speech recognition, Bayesian inference, belief networks, CMLLR, computational complexity, constrained maximum likelihood linear regression, least mean squares methods, LMPSC computation, logarithmic Mel power spectrum, maximum likelihood estimation, Mel frequency cepstral coefficients, MFCC feature vectors, microphone signal, minimum mean square error estimation, model-based feature enhancement, regression analysis, reverberant speech recognition, reverberation, RIR energy, room impulse response, speech recognition, stochastic observation model, stochastic processes}},
  number       = {{7}},
  pages        = {{1692--1707}},
  title        = {{{Model-Based Feature Enhancement for Reverberant Speech Recognition}}},
  doi          = {{10.1109/TASL.2010.2049684}},
  volume       = {{18}},
  year         = {{2010}},
}

@inproceedings{11939,
  abstract     = {{In this paper a switching linear dynamical model (SLDM) approach for speech feature enhancement is improved by employing more accurate models for the dynamics of speech and noise. The model of the clean speech feature trajectory is improved by augmenting the state vector to capture information derived from the delta features. Further a hidden noise state variable is introduced to obtain a more elaborated model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried out by a bank of extended Kalman filters, whose outputs are combined according to the a posteriori probability of the individual state models. Experimental results on the AURORA2 database show improved recognition accuracy.}},
  author       = {{Windmann, Stefan and Haeb-Umbach, Reinhold}},
  booktitle    = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008)}},
  keywords     = {{a posteriori probability, AURORA2 database, Bayesian inference, Bayes methods, channel bank filters, extended Kalman filter banks, hidden noise state variable, Kalman filters, noise dynamics, speech enhancement, speech feature enhancement, speech feature trajectory, switching linear dynamical model approach}},
  pages        = {{4409--4412}},
  title        = {{{Modeling the dynamics of speech and noise for speech feature enhancement in ASR}}},
  doi          = {{10.1109/ICASSP.2008.4518633}},
  year         = {{2008}},
}