Hierarchical Neural Network Structures for Phoneme Recognition (Signals and Communication Technology) by Wolfgang Minker, PDF 3642432107

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

  • Title: Hierarchical Neural Network Structures for Phoneme Recognition (Signals and Communication Technology)
  • Autor: Wolfgang Minker
  • Publisher (Publication Date): Springer; 2013 edition (November 9, 2014)
  • Language: English
  • ISBN-10: | 3642432107
  • ISBN-13: | 978-3642432101
  • File Format: EPUB, PDF

 
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.

No reviews

Comments:

This is a really great book on how to make machine learning much more adaptive for dynamic sequential data.


Related posts

Java Software Solutions Plus MyLab Programming with Pearson eText — Access Card Package (9th Edition) by William Loftus, PDF 0134700031
Android Studio 3.0 Development Essentials – Android 8 Edition by Neil Smyth, PDF 1977540090
Hacking: The No-Nonsense Guide: Learn Ethical Hacking Within 12 Hours! (Cyberpunk Programming Series) (Volume 2) by Cyberpunk University, PDF 154279367X
Towards Reliable IMS-based Networks: Principles, Analysis and Application by Nabil Hmina, PDF 3330062088
VMware Performance and Capacity Management – Second Edition by Iwan ‘e1’ Rahabok, PDF 1785880314
Intelligent Techniques for Data Science by Priti Srinivas Sajja, PDF 3319292056

Leave a Reply

Your email address will not be published. Required fields are marked *