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.
Cyberbullying can have a deep and long lasting impact on its victims, who are often adolescents. Accurately detecting cyberbullying helps prevent it. However, the noise and errors in social media posts and messages make detecting cyberbullying very challenging. In this paper, we propose a novel pronunciation based convolutional neural network (PCNN) to address this challenge. Upon observing that the...
In the paper, we present a method for evaluating the quality of tongue images in Traditional Chinese Medicine (TCM). First, we preprocess the original images to segment the tongue images. Second, geometric features, texture features and spectral entropy features and spatial entropy features based on Spatial-Spectral Entropy-based Quality (SSEQ) index of tongue images are extracted respectively to...
Sparse coding has shown its great potential in learning image feature representation. Recent developed methods such as group sparse coding prefer discovering the group relationships among examples and have achieved the state-of-the-art results in image classification. However, they suffer from poor robustness shortcomings in practice. This paper proposes a robust weighted supervised sparse coding...
In this paper an image splicing detection scheme is proposed. The scheme is based on image quality and analysis of variance. Four kinds of noise used to simulated the image quality changes which caused by tampering of images, and analysis of variance is used to selected the image quality measures which are more sensitive to image blind splicing detection. Combined with the characteristic function...
Recently, using maximum likelihood linear regression (MLLR) transforms as the features for SVM based speaker recognition has been proposed. This can achieve performance comparable to that obtained with state-of-the-art approaches. In this paper, we focus on calculating the transforms based on a GMM universal background model (UBM). Rather than estimating the transforms using maximum likelihood criterion,...
Gaussian mixture models with an universal background model (UBM) have been the standard method for speaker recognition. Typically, maximum a posteriori (MAP) or maximum likelihood linear regression (MLLR) is used to adapt the means of the UBM. Together with the SVM modeling technique, these approaches can achieve excellent performance. MLLR is quite efficient when the amount of adaptation data is...
Token-based approaches have proven quite effective for spoken language identification (LID). Traditionally, Speech utterances are first decoded into token sequences, and then LID tasks are performed on these token sequences by either n-gram language models or support vector machines. In this paper, we propose a hierarchical system design, which utilizes a group of bayesian logistic regression models...
Perceptual user interface takes advantage of human perceptual capabilities in order to present semantical information in native and natural ways. In this paper, we present a novel approach to provide users with an accelerometer-based interface for interactively controlling not only functions or devices in digital environments but virtual characters in game-like scenarios. A general approach suitable...
Most of the methods of Chinese chunking are to re-realize the method of English chunking so as to identify Chinese phrases, which is not only waste manpower but also waste time. In this paper, a multi-agent strategy for English chunking is proposed first, whose F??-1 value reaches 95.70%,which is higher than other else methods. Next, through replacing the English part of speech , phrase tags and repository...
In order to improve the precise rate and recall rate of Chinese text classifier, an improved bagging algorithm - attribute bagging is used in this paper. Document is represented by vector space model and information gain is used to do the feature selection. Re-sampling attributes is used to get multiple training sets and the kNN is selected as the individual classifier. The classification result is...
Most fuzzy support machines (FSVM) canpsilat effectively distinguish between valid samples and outliers or noises. A fuzzy support vector machine based on the fuzzy connectedness is improved in this paper. The fuzzy connectedness proposed for the measurement of the inaccuracy of samples effectively distinguishes between valid samples and outliers or noises. In the FSVM method, a membership function...
Maximum likelihood linear regression (MLLR) is a widely used technique for speaker adaptation in large vocabulary speech recognition system. Recently, using MLLR transforms as features for SVM based speaker recognition tasks has been proposed, achieving performance comparable to that obtained with cepstral features. In this paper, we focus on calculating the transforms based on a GMM universal background...
In this paper, we present a new modeling approach for speaker recognition, which uses a kind of novel phonotactic information as the feature for S VM modeling. Gaussian mixture models (GMMs) have been proven extremely successful for text- independent speaker recognition. The GMM universal background model (UBM) is a speaker-independent model, each component of which can be considered to be modeling...
In order to improve the classification performance of classifiers, an approach of multiple classifiers ensemble based on feature selection (FSCE) is proposed in the paper. After attributes of the training data set are specially selected, the new data set is mapped into new training data sets. There is the number of attributes (the class attribute excepted) of the new data sets. Then classifiers with...
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.