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.
In this paper, we present an acoustic keyword spotter that operates in two stages, detection and verification. In the detection stage, keywords are detected in the utterances, and in the verification stage, confidence measures are used to verify the detected keywords and reject false alarms. A new confidence measure
Being able to search for words or phrases in historic handwritten documents is of paramount importance when preserving cultural heritage. Storing scanned pages of written text can save the information from degradation, but it does not make the textual information readily available. Automatic keyword spotting systems
In this paper we propose a new technique for robust keyword spotting that uses bidirectional long short-term memory (BLSTM) recurrent neural nets to incorporate contextual information in speech decoding. Our approach overcomes the drawbacks of generative HMM modeling by applying a discriminative learning procedure
methods for Indonesian corpus is rather small. Brace well's algorithm has been proven effective in identifying topics in English and Japanese corpora with high accuracy. This paper implements a method for TID based on Brace well's keywords similarity algorithm and the top-n keywords selection for Indonesian news documents
Handwritten word spotting aims at making document images amenable to browsing and searching by keyword retrieval. In this paper, we present a word spotting system based on Hidden Markov Models (HMM) that uses trained subword models to spot keywords. With the proposed method, arbitrary keywords can be spotted that do
paper, we propose a Bayesian approach to region-based image annotation, which integrates the content-based search and context into a unified framework. The content-based search selects representative keywords by matching an unlabeled image with the labeled ones followed by a weighted keyword ranking, which are in turn used
Web-based mapping applications such as Google Maps or Virtual Earth have become increasingly popular. However, current map search is still keyword-based and supports a limited number of spatial predicates. In this paper, we build towards a natural language query interface to spatial databases to answer crime-related
order to achieve it, it is necessary to verify the practicability in various disciplinary fields. The ACCS requires myDBc that is a keyword database to support the course classification. However, it is practically difficult to construct keyword databases to all disciplinary fields in advance. We therefore aim to
system to assist the users in easily accessing the information and have an enjoyable experience browsing Kotenseki images. There are two main functions comprising keyword-based and image-based queries. We also provide automatic detection of objects within the original images to create a database of feature vectors. Our
on keyword matching, analyzes the similarity between the multiple vulnerabilities according to the threshold from the training set, and computes the parallel relationship between the multiple vulnerabilities and discovery the parallel vulnerabilities. Finally, this method is correct and effective by the experimental
This study introduces an example-based chat-oriented dialogue system with personalization framework using long-term memory. Previous representative chat-bots use simple keyword and pattern matching methodologies. To maintain the quality of systems, generating numerous heuristic rules with human labour is inevitable
commercial web search engines, a large fraction of returned images is not related to the query keyword. We present a SVM based active learning approach to selecting relevant images from noisy image search results. The resulting database is more diverse with more sample images, compared with other well established facial
a word-dependent system using the Arabic isolated word /ns10 as10 cs10 as10 ms10//[unk]/ a single keyword for the test utterance. This choice has been made because the word /ns10 as10 cs10 as10 ms10//[unk]/ is mostly used by the Arabic speakers. Speech features are extracted using MFCC. The HTK is used to implement the
The biggest bottleneck of face recognition is the insufficient training samples of face images. In reality, face possess varying nature of expressions, illumination, poses, etc. There is a constrained of insufficient training samples due to number of reasons which reduces the accuracy of face recognition techniques. A method to generate various symmetrical face images by exploiting the axis-symmetrical...
This paper proposes a symbol feature-based hidden Markov model (HMM). Each state in the model is expressed by some symbol features, and is described by feature lists that draw from regular expressions and text inference; based on which, we use Viterbi Algorithm to extract the information from scientific researcherspsila homepages. It works well although there is great information redundancy.
In this paper, we propose a novel system for word spotting and regular expression detection in Handwritten documents. The proposed approach is lexicon-free, i.e., able to spot arbitrary keywords that are not required to be known at the training stage. Furthermore, the proposed system is segmentation-free, i.e., text
Image annotation is the process of assigning proper keywords to describe the content of a given image, which can be regarded as a problem of multi-object image classification. In this paper, a general multi-label annotation algorithm is proposed, which is based on sparse representation theory and employs a multi-level
filtering recommendation is implemented using intelligent agents. The agents work together for recommending meaningful training courses and updating the course information. The system uses a users profile and keywords from courses to rank courses. A ranking accuracy for courses of 90% is achieved while flexibility is achieved
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.