Rhee Man Kil

Learn More
This paper presents a new approach to an auditory model for robust speech recognition in noisy environments. The proposed model consists of cochlear bandpass lters and nonlinear operations in which frequency information of the signal is obtained by zero-crossing intervals. Intensity information is also incorporated by a peak detector and a compressive(More)
Deep learning methods endeavor to learn features automatically at multiple levels and allow systems to learn complex functions mapping from the input space to the output space for the given data. The ability to learn powerful features automatically is increasingly important as the volume of data and range of applications of machine learning methods(More)
This paper presents a method for solving inverse mapping of a continuous function learned by a multilayer feedforward mapping network. The method is based on the iterative update of input vector toward a solution, while escaping from local minima. The input vector update is determined by the pseudo-inverse of the gradient of Lyapunov function, and, should(More)
The output of a classifier is usually determined by the value of a discriminant function and a decision is made based on this output which does not necessarily represent the posterior probability for the soft decision of classification. In this context, it is desirable that the output of a classifier be calibrated in such a way to give the meaning of the(More)
This paper presents a new method of sound segregation based on zero-crossings generated from binaural filter-bank outputs. In our approach, sound source directions are identified using the spatial cues such as inter-aural time differences (ITDs) and inter-aural intensity differences (IIDs). The estimation of ITDs is performed using zero-crossings generated(More)
This paper presents a novel method of classifying media data whether they include X-rated contents or not. In our work, the classification of media data is performed using the class probability output network (CPON) which estimates the conditional class probability. Consequently, the classification of media data can be done using the degree of confidence(More)
This paper presents a new method of zero-crossing based binaural mask estimation for missing data speech recognition under the condition that multiple sound sources are present simultaneously. The masking is determined by the estimated directions of sound sources using the spatial cues such as inter-aural time differences (ITDs) and inter-aural intensity(More)