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.
families, alphabets, phone sets and vocabulary sizes. In particular, it looks at ensembles of stimulated networks to ensure that improved generalisation will withstand system combination effects. In order to assess stimulated training beyond 1-best transcription accuracy, this paper looks at keyword search as a proxy for
Spoken keyword recognition has been under the spotlight for the past several decades, but has gained significant attention in recent years due to the rapid increase in front-end technology applications for mobile and wearable computing. This work presents the trade-off in performance between Artificial Neural Networks
In this paper we present a novel descriptor and method for segmentation-based keyword spotting. We introduce Zoning-Aggregated Hypercolumn features as pixel-level cues for document images. Motivated by recent research in machine vision, we use an appropriately pretrained convolutional network as a feature extraction
spontaneous speech with momentous word error rate, which is a negative aspect of standard retrieval system. To prevail over such a constraint, we propose a method for spoken document retrieval based on spoken keyword spotting using Auto Associative Neural Networks (AANN). The proposed work concerns the exploit of the
was by keyword indexing, or simply by browsing. Digital images databases however, open the way to content-based searching. In this paper we survey some technical aspects of current content-based image retrieval systems based on several neural network architectures. Firstly we discuss the image retrieval system based on
This paper investigates the effectiveness of knowledge distillation in the context of multilingual models. We show that with knowledge distillation, Long Short-Term Memory(LSTM) models can be used to train standard feed-forward Deep Neural Network (DNN) models for a variety of low-resource languages. We then examine how the agreement between the teacher's best labels and the original labels affects...
Image search re-ranking, as an effective tool to improve the text-based image search result, has been adopted by many commercial search engines nowadays. Given a query keyword, images are first retrieved based on the textual information. Then visual features are extracted from images to reorder them by mining their
The World Wide Web has brought us a vast amount of online information. When we search with a keyword, data feedback from many different websites and the user cannot read all the information. So that, text summarization has become a hot topic, it has attracted experts in data mining and natural language processing
In this paper, a novel method is proposed using color and pattern information for recognizing some emotions included in a textile. Here we use 10 Kobayashi emotion keywords. Our method is composed of feature extraction and classification. For accurate emotion recognition, both color and pattern are extracted from a
utilized a recurrent structure to detain the contextual information from word embedding features. Max pooling layer was configured to extract important semantic keywords from the text. We evaluated our approach on two benchmark PPI datasets BioCreative II and BioCreative III. An experimental results show that RCNN based
This paper presents a Semantic Attribute assisted video SUMmarization framework (SASUM). Compared with traditional methods, SASUM has several innovative features. Firstly, we use a natural language processing tool to discover a set of keywords from an image and text corpora to form the semantic attributes of visual
recurrent networks. Experimental results showed that multi-Layer preception provided better classification results in conjunction with the empirical mode decomposition. It is also concluded that a small set of features is sufficient to classify galaxy images and provide a fast classification. Keywords: Hubble Sequence
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.