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.
Web-Ear is an information retrieval system in which anyone can search "What person X told about the topic Y" on the internet or in the database of the system. If the search is made on the internet, first the system submits a query to Google search engine and retrieves a set of information. In order to isolate speech portions of retrieved data, an extraction process is required to be performed...
This paper reports an initial study that aims to Chinese multi-document summarization. We introduce and compare different dynamic threshold model which TDT (Topic Detection and Tracking), and get document sets based on topic, then focus on Chinese multi-document summarization generation. Our approaches are based on the combination TDT temporal properties and multi-document summarization. Results show...
This paper introduces the current primary functionalities, characteristics and usages of Unified Minority Speech Parameter Database Platform Software as well as future-expanded functions. By using the platform, we can accomplish acoustic parameter retrieval, statistics and analysis of established Tibetan, Uigur and Yi broadcasting acoustic parameter databases. After adding acoustic parameters of more...
The paper presents a modelling of the human machine dialogue in dual language (French and Arabic). According to the principle of our model the production of a speech result from an exchange between the human and the machine, that depends on the interlocutor's mental condition. It presents itself under the set of fundamental units of the memory (FUM). The hierarchical organization of these units permits...
According to the characteristic of the Chinese speech, we propose a method of retrieving the Chinese speech based on wavelet transform in this paper. At first we preprocess the data in the warehouse to provide the high quality speech data. And then we divided the speech samples into subsections and pick up the character of them. Finally, based on the Euclid distance of scale parts, we retrieve the...
Cross-lingual spoken sentence retrieval (CLSSR) remains a challenge, especially for queries including OOV words such as person names. This paper proposes a simple method of fuzzy matching between query names and phones of candidate audio segments. This approach has the advantage of avoiding some word decoding errors in automatic speech recognition (ASR). Experiments on Mandarin-English CLSSR show...
The following topics are dealt with: knowledge management, reasoning, neural networks, and evolutionary programming; image processing and pattern recognition; machine learning and data mining; natural language processing and speech recognition; information retrieval; multi-agent systems and ontologies; bioinformatics and medical applications; intelligent tutoring systems; formal languages and automations;...
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.