Central Library

Normal view MARC view ISBD view

Hierarchical Neural Network Structures for Phoneme Recognition [electronic resource] / by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker.

By: Vasquez, Daniel [author.].
Contributor(s): Gruhn, Rainer [author.] | Minker, Wolfgang [author.] | SpringerLink (Online service).
Material type: materialTypeLabelBookSeries: Signals and Communication Technology: Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2013Description: XVIII, 134 p. online resource.Content type: text Media type: computer Carrier type: online resourceISBN: 9783642344251.Subject(s): Engineering | User interfaces (Computer systems) | Computational linguistics | Computational intelligence | Engineering | Signal, Image and Speech Processing | User Interfaces and Human Computer Interaction | Computational Intelligence | Language Translation and LinguisticsAdditional physical formats: Printed edition:: No titleDDC classification: 621.382 Online resources: Click here to access online
Contents:
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.
In: Springer eBooksSummary: 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.
    average rating: 0.0 (0 votes)
No physical items for this record

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.

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.

There are no comments for this item.

Log in to your account to post a comment.