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.
Markov Model/ Artificial Neural Network (HMM/ANN) keyword spotting framework. The feature extraction method used was Mel-Frequency Cepstral Coefficients (MFCC). The ANN is a 3-layer feedforward neural network using Multi-Layer Perceptron (MLP). In recognizing the words, an HMM decoder was used which implemented the Viterbi
This work demonstrates the development of Keyword Spotting (KWS) system using Vowel Onset Point (VOP), Vector Quantization (VQ) and Hidden Markov Model(HMM) based techniques. The goal of KWS system is to spot the keywords present in the test speech signal, while neglecting rest of the words. In this work, first
some manufacturing and logistical operations, or for information retrieval from large audio archives. We investigate the use of three keyword spotting techniques and compare them with a classic large vocabulary sp eech reco gnit ion sy st em. To evaluat e t heir performance, we specified and studied two model applications
General purpose computation based on GPU is a hot topic for research in recent years. The paper presents the parallel implementation of Viterbi algorithm on GPU based on features of GPU and characteristics of Viterbi algorithm in keyword spotting system. The results of examination by using NVIDIA 9600 GT GPU show that
segmentation. A keyword is represented by concatenating its character models. We propose and compare two systems: a script identifier based (IDB) and a script identifier free (IDF) system. IDB uses a HMM based script identifier before spotting a keyword. While, IDF does the spotting without the script identification. The system
. Network weights and RBF centers are trained at the word level to produce a high score for the correct keyword hits and a low score for false alarms generated by nonkeyword speech. Preliminary experiments using this approach are exploring a constructive approach which adds RBF centers to model nonkeyword near-misses and a
learning approach. We use a graphical model, Dynamic Conditional Random Fields (DCRFs), for training our classifier. Our approach is based on semantic analysis of text to classify the predicates describing coexpression relationship rather than detecting the presence of keywords. We compared our results of sentence
and converts it into routing keywords. Accent identification is the most important factor for improving the performance of natural language call-routing systems because accents vary widely, even within the same country or community. This variation occurs when non-native speakers start to learn a second language; the
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.