The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
As an important part of ICT in education, teacher's ICT application ability in teaching and research is vital to improve teachers' professional development and to promote the education modernization. Understanding the development of teacher's ICT application ability in foreign countries and analyzing the difference between teacher's application ability in urban and rural are an important reference...
In this letter, we propose a new detection framework based on robust invariant generalized Hough transform (RIGHT) to solve the problem of detecting inshore ships in high-resolution remote sensing imagery. The invariant generalized Hough transform is an effective shape extraction technique, but it is not adaptive to shape deformation well. In order to improve its adaptability, we use an iterative...
This paper presents a feature-transform based approach to unsupervised task adaptation and personalization for speech recognition. Given task-specific speech data collected from a deployed service, an “acoustic sniffing” module is built first by using a so-called i-vector technique with a number of acoustic conditions identified via i-vector clustering. Unsupervised maximum likelihood training is...
This paper presents a comparative study of two discriminatively trained feature transform approaches, namely feature-space minimum phone error (fMPE) and region-dependent linear transform (RDLT), to large vocabulary continuous speech recognition (LVCSR). Experiments are performed on an LVCSR task of conversational telephone speech transcription using about 2,000 hours training data. Starting from...
Recently, we proposed an i-vector approach to acoustic sniffing for irrelevant variability normalization based acoustic model training in large vocabulary continuous speech recognition (LVCSR). Its effectiveness has been confirmed by experimental results on Switchboard- 1 conversational telephone speech transcription task. In this paper, we study several discriminative feature extraction approaches...
Recently, Dozens of applications for sparse representation has been developed. The model with l0-norm as constraint is an NP hard problem. How to find the global optimal solution is a difficult point of this area. For genetic algorithm is good at solving NP hard problem, a dictionary training method based on it is proposed in this paper. The samples are first classified randomly for generate original...
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large vocabulary continuous speech recognition. A speaker-clustering based method is used for acoustic sniffing and maximum mutual information (MMI) is used as a training criterion. Combined with unsupervised adaptation of feature...
Over the past few years, multi-view face detection issue has become one of the most attractive research topics in the field of computer vision. In this paper, a novel automatic system for multi-view face detection and pose estimation is proposed. Our approach adopts modified appearance-based learning methods to build corresponding face detectors and pose estimators, and detects multi-view faces according...
In recent years, research on dictionary design for sparse representation (SR) has changed from pre-defined to training. A Hierarchical K-means Clustering (HKC) dictionary training algorithm is proposed in this paper. The algorithm presents a framework for SR for a class of images. HKC used K-means clustering to generate atoms which is one to one corresponding to hyperplanes for approximating hyperspherical...
Malware obfuscation is defined as a program transformation. It is always used in malware to evade detection from anti-malware software. In this paper, we propose a method to detect malware obfuscation using maximal patterns. Maximal pattern is a subsequence in malware's runtime system call sequence, which frequently appears in program execution, and can be used to describe the program specific behavior...
We study the problem of detecting and profiling terrorists using a combination of an ensemble classifier, namely random forest and relational information. Given a database for a set of individuals characterized by both "local" attributes such as age and criminal background, and "relational" information such as communications among a subset of the individuals, with a subset of the...
In this paper, the authors established an evaluation model of university teaching quality based on back-propagation neural networks. Quantified indices of teaching quality were inputs of the model, while teaching effect was output. The empirical research by MATLAB showed that this evaluation approach was suitable for the university teaching quality assessment tasks, which not only overcomes subjective...
Support vector machine (SVM) has been a promising method for data mining and machine learning in recent years. However, the training complexity of SVM is highly dependent on the size of a data set. A cluster support vector machines (C-SVM) method for large-scale data set classification is presented to accelerate the training speed. By calculating cluster mirror radius ratio and representative sample...
Support vector machine (SVM) has been a promising method for data mining and machine learning in recent years. However, the training complexity of SVM is highly dependent on the size of a data set. A preprocessing support vector machines (P-SVM) method for large-scale data set classification is presented to speed up SVM training. By analyzing the neighbor classification feature for each sample in...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.