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.
When applied to speech, Non-negative Matrix Factorization is capable of learning a small vocabulary of words, foregoing any prior linguistic knowledge. This makes it adequate for small-scale speech applications where flexibility is of the utmost importance, e.g. assistive technology for the speech impaired. However, its performance depends on the way its inputs are represented. We propose the use...
This paper describes experiments for audio clips comparison based on spoken context. The spoken content is obtained using automatic speech recognition. The social tags that are available for most of the audio clips are used as keywords. These keywords are mapped to the spoken transcription representing the audio clips
In this paper, we studied a speaker independent isolated speaker recognition system for Turkish language by using cross correlation technique. The power spectrumpsilas of each keyword speech for different speakerpsilas determined using the linear predictive coding in order to constitute a feature vectors database that
In this paper we present a spoken query detection method based on posteriorgrams generated from Deep Boltzmann Machines (DBMs). The proposed method can be deployed in both semi-supervised and unsupervised training scenarios. The DBM-based posteriorgrams were evaluated on a series of keyword spotting tasks using the
In this paper we present our recent work in implementing Serbian spoken dialogue system for the bus information retrieval at the main Belgrade bus station. Dialogue is organized into several levels. At each level, system has to recognize a limited number of keywords in continuous speech of Serbian. The keywords were
application of CVA, word spotting in continuous speech. Two different recordings containing ten keywords were used for training and testing. A Hundred percent successful recognition was achieved with the aid of a pre-calculated decision threshold. However, the aim was to develop an algorithm independent of databases so a method
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.