#### Filter Results:

#### Publication Year

1984

1997

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

This paper investigates two methods to define a distance measure between any pair of Hidden Markov Models (HMM). The first one is the geometricaly motivated euclidean distance which solely incorporates the feature probabilities. The second measure is the Kulback-Liebler distance which is based on the discriminating power of the probability measure on the… (More)

In this paper we present a robust speaker independent speech recognition system consisting of a feature extraction based on a model of the auditory periphery, and a Locally Recurrent Neural Network for scoring of the derived feature vectors. A number of recognition experiments were carried out to investigate the robustness of this combination against… (More)

A learning procedure for the dynamics of cellular neural networks (CNN) with nonlinear cell interactions is presented. It is applied in order to nd the parameters of CNN that model the dynamics of certain nonlinear systems, which are characterized by partial diierential equations (PDE). Values of a solution of the considered PDE for a particular initial… (More)

CELP schemes with trained excitation codebook are able to reproduce more complex waveforms than stochastic CELP schemes. Here we present a new algorithm for the design of trained CELP excitation code-books which are well adapted to the residual of speech even in transition regions. The vectors of the excitation codebook are adapted to a training speech… (More)

The computational complexity of speech recognizers based on fully connected recurrent neural networks, i.e. the large number of connections, prevents a hardware realization. We introduced locally connected recurrent neural networks in order to keep the properties of recurrent neural networks and to reduce the connectivity density of the network. A special… (More)

Speech coding systems for mobile communication have to cope with noisy channels. In particular, vector quantization as central data reduction scheme is highly sensitive to transmission errors due to the low redundancy in the encoded data. Here we present three methods for the design of a vector quantizer with enhanced robustness against transmission errors.… (More)