000 -LEADER |
fixed length control field |
02712nam a22004575i 4500 |
003 - CONTROL NUMBER IDENTIFIER |
control field |
OSt |
005 - DATE AND TIME OF LATEST TRANSACTION |
control field |
20140310143354.0 |
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION |
fixed length control field |
cr nn 008mamaa |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
fixed length control field |
121026s2013 gw | s |||| 0|eng d |
020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
International Standard Book Number |
9783642344251 |
|
978-3-642-34425-1 |
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER |
Classification number |
621.382 |
Edition number |
23 |
264 #1 - |
-- |
Berlin, Heidelberg : |
-- |
Springer Berlin Heidelberg : |
-- |
Imprint: Springer, |
-- |
2013. |
912 ## - |
-- |
ZDB-2-ENG |
100 1# - MAIN ENTRY--PERSONAL NAME |
Personal name |
Vasquez, Daniel. |
Relator term |
author. |
245 10 - IMMEDIATE SOURCE OF ACQUISITION NOTE |
Title |
Hierarchical Neural Network Structures for Phoneme Recognition |
Medium |
[electronic resource] / |
Statement of responsibility, etc |
by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker. |
300 ## - PHYSICAL DESCRIPTION |
Extent |
XVIII, 133 p. 49 illus. |
Other physical details |
online resource. |
440 1# - SERIES STATEMENT/ADDED ENTRY--TITLE |
Title |
Signals and Communication Technology, |
International Standard Serial Number |
1860-4862 |
505 0# - FORMATTED CONTENTS NOTE |
Formatted contents note |
Background in Speech Recognition -- Phoneme Recognition Task -- Hierarchical Approach and Downsampling Schemes -- Extending the Hierarchical Scheme: Inter and Intra Phonetic Information -- Theoretical framework for phoneme recognition analysis. |
520 ## - SUMMARY, ETC. |
Summary, etc |
In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach. |
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM |
Topical term or geographic name as entry element |
Engineering. |
|
Topical term or geographic name as entry element |
Computer science. |
|
Topical term or geographic name as entry element |
Translators (Computer programs). |
|
Topical term or geographic name as entry element |
Engineering. |
|
Topical term or geographic name as entry element |
Signal, Image and Speech Processing. |
|
Topical term or geographic name as entry element |
User Interfaces and Human Computer Interaction. |
|
Topical term or geographic name as entry element |
Computational Intelligence. |
|
Topical term or geographic name as entry element |
Language Translation and Linguistics. |
700 1# - ADDED ENTRY--PERSONAL NAME |
Personal name |
Gruhn, Rainer. |
Relator term |
author. |
|
Personal name |
Minker, Wolfgang. |
Relator term |
author. |
710 2# - ADDED ENTRY--CORPORATE NAME |
Corporate name or jurisdiction name as entry element |
SpringerLink (Online service) |
773 0# - HOST ITEM ENTRY |
Title |
Springer eBooks |
776 08 - ADDITIONAL PHYSICAL FORM ENTRY |
Display text |
Printed edition: |
International Standard Book Number |
9783642344244 |
856 40 - ELECTRONIC LOCATION AND ACCESS |
Uniform Resource Identifier |
http://dx.doi.org/10.1007/978-3-642-34425-1 |
942 ## - ADDED ENTRY ELEMENTS (KOHA) |
Source of classification or shelving scheme |
|
Item type |
E-Book |