Hierarchical Neural Network Structures for Phoneme Recognition
Seiten
2012
|
2013
Springer Berlin (Verlag)
978-3-642-34424-4 (ISBN)
Springer Berlin (Verlag)
978-3-642-34424-4 (ISBN)
The subject of this study is the role of hierarchical structures, based on neural networks, in identifying phonemes in automated speech recognition systems. It shows how the artificial neural network paradigm can simplify the analysis of spoken language.
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.
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.
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.
From the reviews:
"This brief book comes packed with useful information about some novel techniques for the recognition of speech building blocks known as phonemes. ... it is brimming with useful and well-presented information. I recommend it for graduate students in the field, as well as for practicing professionals." (Vladimir Botchev, Computing Reviews, May, 2013)Erscheint lt. Verlag | 18.10.2012 |
---|---|
Reihe/Serie | Signals and Communication Technology |
Zusatzinfo | XVIII, 134 p. |
Verlagsort | Berlin |
Sprache | englisch |
Maße | 155 x 235 mm |
Gewicht | 379 g |
Themenwelt | Technik ► Elektrotechnik / Energietechnik |
Schlagworte | articulatory attributes • Artificial Neural Network • HMM/ANN • Hybrid Hidden Markov Model • Multilayered Perceptron MLP • Neuronale Netze • phoneme recognition • phonetic decoder • phonotactics • Spoken language dialogue systems • TIMIT database |
ISBN-10 | 3-642-34424-0 / 3642344240 |
ISBN-13 | 978-3-642-34424-4 / 9783642344244 |
Zustand | Neuware |
Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Kolbenmaschinen - Strömungsmaschinen - Kraftwerke
Buch | Hardcover (2023)
Hanser (Verlag)
49,99 €