Hierarchical Neural Network Structures for Phoneme Recognition (Signals and Communication Technology)

by Daniel Vasquez, Rainer Gruhn, and Wolfgang Minker

0 ratings • 0 reviews • 0 shelved
Book cover for Hierarchical Neural Network Structures for Phoneme Recognition

Bookhype may earn a small commission from qualifying purchases. Full disclosure.

In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are mainly evaluated within the phoneme recognition task under the Hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) paradigm. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron (MLP). Additionally, the output of the first level is used as an input for the second level. This system can be substantially speeded up by removing the redundant information contained at the output of the first level.
  • ISBN13 9783642432101
  • Publish Date 9 November 2014 (first published 18 October 2012)
  • Publish Status Active
  • Publish Country DE
  • Publisher Springer-Verlag Berlin and Heidelberg GmbH & Co. KG
  • Imprint Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • Format Paperback
  • Pages 134
  • Language English