Large-margin discriminative training of hidden Markov models has received significant attention recently. A natural and interesting question is whether the existing discriminative training algorithms can be extended directly to embed the concept of margin. In this paper, we give this question an affirmative answer by showing that the sigmoid bias in the conventional minimum classification error...

Previous research has shown that perceptual training in peripheral vision, using a letter-recognition task, increases reading speed and letter recognition (S. T. L. Chung, G. E. Legge, & S. H. Cheung, 2004). We tested the hypothesis that enhanced deployment of spatial attention to peripheral vision explains this training effect. Subjects were pre- and post-tested with 3 tasks at 10° above and b...

Research in the field of face recognition has been popular for several decades. With advances in technology, approaches to solving this problems haves changed. Main goal of this paper was to compare different training algorithms for neural networks and to apply them for face recognition as it is a nonlinear problem. Algorithm that we have used for face recognition problem was the Eigenface algo...

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments use standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss in recognition performance for toll quality speech...

We propose an incremental unsupervised adaptation method based on reinforcement learning in order to achieve robust speech recognition in various noisy environments. Reinforcement learning is a training method based on rewards that represents correctness of outputs instead of supervised data. The training progresses gradually based on rewards given. Our method is able to perform environmental a...

In statistical pattern recognition, parameters of distributions are usually estimated from training samples. It is well known that shortage of training samples causes estimation errors which reduce recognition accuracy. By studying estimation errors of eigenvalues, various methods of avoiding recognition accuracy reduction have been proposed. However, estimation errors of eigenvectors have not ...

MESSAGEPAD and EMATE. Combining an artificial neural network (ANN) as a character classifier with a context-driven search over segmentation and word-recognition hypotheses provides an effective recognition system. Long-standing issues relative to training, generalization, segmentation, models of context, probabilistic formalisms, and so on, need to be resolved, however, to achieve excellent per...

A technique to peform speech recognition directly from audio files encoded using the MPEG/Audio coding standard is described. The technique works in the compressed domain and does not require the MPEG/Audio file to be decompressed. Only the encoded subband samples are extracted and processed for training and recognition. The underlying speech recognition engine used is based on the Hidden Marko...

Appearance-based object recognition systems rely on training from imagery, which allows the recognition of objects without requiring a 3D geometric model. It has been little explored whether such systems can be trained from imagery that is unlabeled, and whether they can be trained from imagery that is not trivially segmentable. In this paper we present a method for minimally supervised trainin...