Connectionist Speech Recognition: A Hybrid ApproachSpringer Science & Business Media, 1994 - 312 lappuses Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state of the art continuous speech recognition systems based on hidden Markov models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e. HMM emission probability estimation and feature extraction. The book describes a successful five-year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical systems. Using standard databases and comparison with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods. Connectionist Speech Recognition is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. The book is also suitable as a text for advanced courses on neural networks or speech processing. |
No grāmatas satura
1.–5. rezultāts no 60.
3. lappuse
Atvainojiet, šīs lappuses saturs ir ierobežots..
Atvainojiet, šīs lappuses saturs ir ierobežots..
4. lappuse
Atvainojiet, šīs lappuses saturs ir ierobežots..
Atvainojiet, šīs lappuses saturs ir ierobežots..
5. lappuse
Atvainojiet, šīs lappuses saturs ir ierobežots..
Atvainojiet, šīs lappuses saturs ir ierobežots..
6. lappuse
Atvainojiet, šīs lappuses saturs ir ierobežots..
Atvainojiet, šīs lappuses saturs ir ierobežots..
7. lappuse
Atvainojiet, šīs lappuses saturs ir ierobežots..
Atvainojiet, šīs lappuses saturs ir ierobežots..
Saturs
INTRODUCTION | vii |
STATISTICAL PATTERN CLASSIFICATION | xix |
HIDDEN MARKOV MODELS | 1 |
MULTILAYER PERCEPTRONS | 33 |
SPEECH RECOGNITION USING ANNs | 57 |
STATISTICAL INFERENCE IN MLPs | 89 |
THE HYBRID HMMMLP APPROACH | 129 |
EXPERIMENTAL SYSTEMS | 159 |
TRAINING HARDWARE AND SOFTWARE | 197 |
CROSSVALIDATION IN MLP TRAINING | 207 |
HMMMLP AND PREDICTIVE MODELS | 217 |
FEATURE EXTRACTION BY MLP | 227 |
FINAL SYSTEM OVERVIEW | 241 |
CONCLUSIONS | 249 |
Bibliography | 255 |
281 | |
Citi izdevumi - Skatīt visu
Connectionist Speech Recognition: A Hybrid Approach Hervé A. Bourlard,Nelson Morgan Ierobežota priekšskatīšana - 2012 |
Connectionist Speech Recognition: A Hybrid Approach Hervé A. Bourlard,Nelson Morgan Priekšskatījums nav pieejams - 2012 |
Bieži izmantoti vārdi un frāzes
acoustic vectors ANNs associated assumptions autoregressive Bayes cepstral Chapter class qk computation Conf connectionist context context-dependent contextual inputs continuous speech recognition cross-validation database described discriminant functions dynamic programming emission probabilities error feature vector Forward-Backward algorithm frame level Gaussian given hidden layer Hidden Markov Models hidden units hybrid HMM/MLP approach IEEE Proc improve input features input field input pattern input vector Intl iterations linear matrix Maximum Likelihood minimization MLP outputs MLP training Multilayer Perceptron neural networks number of parameters optimal output layer output units output values perceptron performance phone models phoneme possible posterior probabilities prior probabilities probability density functions problem prototype vector RBFs recurrent Section segmentation shown sigmoid function Signal Processing speaker speaker-independent speech recognition systems speech units standard HMMs statistical techniques test set tion topology training data training patterns training set transition probabilities triphone Viterbi algorithm Viterbi search weights word recognition
Populāri fragmenti
v. lappuse - Truth scarce ever yet carried it by vote anywhere at its first appearance: new opinions are always suspected and usually opposed, without any other reason but because they are not already common.
Atsauces uz šo grāmatu
Automatic Speech and Speaker Recognition: Advanced Topics Chin-Hui Lee,Frank K. Soong,Kuldip Paliwal Ierobežota priekšskatīšana - 1996 |
Text, Speech and Dialogue: 7th International Conference, TSD 2004, Brno ... Petr Sojka,Ivan Kopecek,Karel Pala Priekšskatījums nav pieejams - 2004 |