Hierarchical Neural Network Structures for Phoneme Recognition [electronic resource] /by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker.
by Vasquez, Daniel [author.]; Gruhn, Rainer [author.]; Minker, Wolfgang [author.]; SpringerLink (Online service).
Material type:
BookSeries: Signals and Communication Technology: Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg : 2013.Description: XVIII, 133 p. 49 illus. online resource.ISBN: 9783642344251.Subject(s): Engineering | Computer science | Translators (Computer programs) | Engineering | Signal, Image and Speech Processing | User Interfaces and Human Computer Interaction | Computational Intelligence | Language Translation and LinguisticsDDC classification: 621.382 Online resources: Click here to access online | Item type | Current location | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|
| TA1637-1638 (Browse shelf) | Available | ||||
| TK7882.S65 (Browse shelf) | Available | ||||
| Long Loan | MAIN LIBRARY | TK5102.9 (Browse shelf) | Available |
Close shelf browser
| TK7882.S65 Methods of Signal Processing for Adaptive Antenna Arrays | TK7882.S65 Adaptive Digital Filters | TK7882.S65 Study and Design of Differential Microphone Arrays | TK7882.S65 Hierarchical Neural Network Structures for Phoneme Recognition | TK7882.S65 Delta-Sigma A/D-Converters | TK7882.S65 Brain-Computer Interface Research | TK7882.S65 Topological Signal Processing |
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.