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.
A very important step toward the goal of human-computer dialog using natural language is the identification of semantic relations between different constituents of texts or speech. The semantic relations that can be established between the words senses are related to their part-of-speech. Because the noun is one of the most important lexical categories we focused on the semantic relations encoded...
This paper will discuss the progress made in Automatic Speech Recognition and Understanding (ASRU) by applying Deep Learning (DL) in the frame of acoustic modeling. After explaining the concept of DL, specific algorithms like Restricted Bolzmann Machine (RBM), Convolutional Neural Network (CNN), Autoencoder (AE), Deep Belief Network (DBN), will be presented and evaluated. Experiments in the academic...
The natural language processing became one of the most important fields of artificial intelligence because is related to the area of human-computer interaction using human languages (natural language generation, question answering, machine translation, etc.) or speech understanding (language modeling).To model the relations between words it is necessary to find the syntactic and semantic relations...
Language modeling plays an important role in continuous speech recognition and understanding providing an improvement of their performances. But language modeling has been shown to be a difficult task due to the many sources of variability that are present in natural languages. Therefore has been developed different method to process the language. The most used of them are grammar and statistical...
In this paper, we describe an application of speaker verification using Romanian vowels as speaker's models in case of a small Romanian language database. Vowels models are obtained with continuous HMMs using re-training of the vowels models for every speaker. Afterwards the models are classified with the powerful technique named SVM.
The present paper describes the evolution of our work concerning the problem of speech recognition. Beginning with a classical hidden Markov model (HMM), we have investigated two ways to improve the performance of this basic structure. The first way was to realize a neuro-statistical hybrid by integrating a multilayer perceptron (MLP) as a posteriori probability estimator. The system was further refined...
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.