The performance of the non-contact biometric recognition system is commonly poor when the labeled data set is small. To solve this problem, we perform the semi-supervised learning methods on face and gait to exploit the non-contact unlabeled biometric data. In the paper, the most important work is to apply co-training algorithm to the face and gait recognition system. Besides, we perform experi...

The objective of this thesis is to investigate the generation and use of synthetic training data for off-line cursive handwriting recognition. It has been shown in many works before that the size and quality of the training data has a great impact on the performance of handwriting recognition systems. A general observation is that the more texts are used for training, the better recognition per...

In this paper, we generalize the training error definitions for minimum classification error (MCE) training and investigate their impact on recognition performance. Starting the conventional MCE method, we discuss with three issues in regard to training error definition, which may affect the recognizer performance and need to be extensively studied. We focus our discussions on the first two asp...

This paper proposes a new speech recognition algorithm using a new context-dependent recognition unit design method for e cient and precise acoustic modeling. This algorithm uses both training and recognition vocabularies to select context-dependent units which precisely represent acoustic variations due to phonetic contexts in a recognition vocabulary. An e cient training algorithm for selecte...

In this work, we use the PCA based eigenface method to build a face recognition system that have recognition accuracy more than 97% for the ORL database and 100% for the CMU databases. However, the main goal of this research is to identify the characteristics of eigenface based face recognition while, (1) the number of eigenface features or signatures in the training and test data is varied; (2...

Artificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorith...

BACKGROUND The simulation of the CI (cochlear implant) signal presents a degraded representation of each musical instrument, which makes recognition difficult. PURPOSE To examine the efficiency and effectiveness of three types of training on recognition of musical instruments as presented through simulations of the sounds transmitted through a CI. RESEARCH DESIGN Participants were randomly ...

Automatic speech recognition is critical in natural human-centric interfaces for ambient intelligence. The performance of an automatic speech recognition system, however, degrades drastically when there is a mismatch between training and testing conditions. The aim of robust speech recognition is to overcome the mismatch problem so the result is a moderate and graceful degradation in recognitio...

The aim of this work is to build up a common framework for a class of discriminative training criteria and optimization methods for continuous speech recognition. A uni®ed discriminative criterion based on likelihood ratios of correct and competing models with optional smoothing is presented. The uni®ed criterion leads to particular criteria through the choice of competing word sequences and th...

• Implemented corrective training to improve recognition performance; on the standard training set this improves speaker-independent perplexity 60 performance from 6.7% error to 5.1% error, and for a larger training set (about 11,000 sentences), improves speaker-independent recognition from 5.3% error to 4.1% error. Plans • Complete the construction of the current hardware design, and develop s...