Hierarchical Neural Network Structures for Phoneme Recognition / Signals and Communication Technology (PDF)
- Kreditkarte, Paypal, Rechnung
- Kostenloser tolino webreader
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.
- Autoren: Daniel Vasquez , Rainer Gruhn , Wolfgang Minker
- 2012, 2013, 134 Seiten, Englisch
- Verlag: Springer-Verlag GmbH
- ISBN-10: 3642344259
- ISBN-13: 9783642344251
- Erscheinungsdatum: 17.10.2012
Abhängig von Bildschirmgrösse und eingestellter Schriftgrösse kann die Seitenzahl auf Ihrem Lesegerät variieren.
- Dateiformat: PDF
- Grösse: 2.61 MB
- Ohne Kopierschutz
- Vorlesefunktion
Zustand | Preis | Porto | Zahlung | Verkäufer | Rating |
---|
Schreiben Sie einen Kommentar zu "Hierarchical Neural Network Structures for Phoneme Recognition / Signals and Communication Technology".
Kommentar verfassen