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 mainly evaluated within the phoneme recognition task under the Hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) paradigm. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron (MLP). Additionally, the output of the first level is used as an input for the second level. This system can be substantially speeded up by removing the redundant information contained at the output of the first level.

Simplifies the analysis in spoken language dialogue systems Investigates hierarchical structures based on neural networks for automatic speech recognition Written for academic and industrial researchers in speech recognition

Inhalt
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.