Hierarchical Neural Network Structures for Phoneme Recognition

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 o...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: Vasquez, Daniel (Συγγραφέας), Gruhn, Rainer (Συγγραφέας), Minker, Wolfgang (Συγγραφέας)
Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
Γλώσσα:English
Έκδοση: Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2013.
Σειρά:Signals and Communication Technology,
Θέματα:
Διαθέσιμο Online:Full Text via HEAL-Link
LEADER 03073nam a22005655i 4500
001 978-3-642-34425-1
003 DE-He213
005 20151125201046.0
007 cr nn 008mamaa
008 121026s2013 gw | s |||| 0|eng d
020 |a 9783642344251  |9 978-3-642-34425-1 
024 7 |a 10.1007/978-3-642-34425-1  |2 doi 
040 |d GrThAP 
050 4 |a TK5102.9 
050 4 |a TA1637-1638 
050 4 |a TK7882.S65 
072 7 |a TTBM  |2 bicssc 
072 7 |a UYS  |2 bicssc 
072 7 |a TEC008000  |2 bisacsh 
072 7 |a COM073000  |2 bisacsh 
082 0 4 |a 621.382  |2 23 
100 1 |a Vasquez, Daniel.  |e author. 
245 1 0 |a Hierarchical Neural Network Structures for Phoneme Recognition  |h [electronic resource] /  |c by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker. 
264 1 |a Berlin, Heidelberg :  |b Springer Berlin Heidelberg :  |b Imprint: Springer,  |c 2013. 
300 |a XVIII, 134 p.  |b online resource. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
347 |a text file  |b PDF  |2 rda 
490 1 |a Signals and Communication Technology,  |x 1860-4862 
505 0 |a 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 |a 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 |a Engineering. 
650 0 |a User interfaces (Computer systems). 
650 0 |a Computational linguistics. 
650 0 |a Computational intelligence. 
650 1 4 |a Engineering. 
650 2 4 |a Signal, Image and Speech Processing. 
650 2 4 |a User Interfaces and Human Computer Interaction. 
650 2 4 |a Computational Intelligence. 
650 2 4 |a Language Translation and Linguistics. 
700 1 |a Gruhn, Rainer.  |e author. 
700 1 |a Minker, Wolfgang.  |e author. 
710 2 |a SpringerLink (Online service) 
773 0 |t Springer eBooks 
776 0 8 |i Printed edition:  |z 9783642344244 
830 0 |a Signals and Communication Technology,  |x 1860-4862 
856 4 0 |u http://dx.doi.org/10.1007/978-3-642-34425-1  |z Full Text via HEAL-Link 
912 |a ZDB-2-ENG 
950 |a Engineering (Springer-11647)