Paper Info
Title
Hybrid models for automatic speech recognition: a comparison of classical ANN and kernel based methods
Abstract
Support Vector Machines (SVMs) are state-of-the-art methods for machine learning but share with more classical Artificial Neural Networks (ANNs) the difficulty of their application to input patterns of non-fixed dimension. This is the case in Automatic Speech Recognition (ASR), in which the duration of the speech utterances is variable. In this paper we have recalled the hybrid (ANN/HMM) solutions provided in the past for ANNs and applied them to SVMs performing a comparison between them. We have experimentally assessed both hybrid systems with respect to the standard HMM-based ASR system, for several noisy environments. On the one hand, the ANN/HMM system provides better results than the HMM-based system. On the other, the results achieved by the SVM/HMM system are slightly lower than those of the HMM system. Nevertheless, such a results are encouraging due to the current limitations of the SVM/HMM system.
Year
DOI
Venue
2007
10.1007/978-3-540-77347-4_12
NOLISP
Keywords
Field
DocType
input pattern,support vector machines,automatic speech recognition,hmm system,hybrid system,classical artificial neural networks,current limitation,hmm-based system,hybrid model,better result,standard hmm-based asr system,classical ann,hidden markov models,support vector machine,artificial neural networks,hybrid systems,hidden markov model,artificial neural network,machine learning
Kernel (linear algebra),Pattern recognition,Computer science,Support vector machine,Speech recognition,Artificial intelligence,Artificial neural network,Hidden Markov model,Hybrid system
Conference
Volume
ISSN
ISBN
4885
0302-9743
3-540-77346-0
Citations 
PageRank 
References 
3
0.40
7
Authors
4
Name
Order
Citations
PageRank
Ana Isabel Garcia-Moral1131.61
Rubén Solera-Urena2122.27
Carmen Peláez-moreno313022.07
Fernando Díaz-de-María420132.14