Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Modular Neural Networks with Task-Specific Input Parameters for Speakerindependent Speech Recognition

Axel Glaeser

Technical University of Darmstadt, Institute of Telecommunications and Electroacoustics, Darmstadt, Germany

In recent years, the computational effort for novel speech recognition systems has increased much more than the resulting recognition rates. Therefore, we present an approach for overcoming this drawback by using a modular phoneme recognition system. It combines advantages of neural networks with those of modular architectures. Important system features are module-specific selection of input parameters according to the decision tasks and the utilization of time delay neural networks (TDNNs) as well as static neural networks without time processing. The intention is to improve the recognition rate for speaker-independent phoneme recognition and, at the same time, to reduce the necessary effort for simulating the system after the initial learning phase.

Full Paper

Bibliographic reference.  Glaeser, Axel (1995): "Modular neural networks with task-specific input parameters for speakerindependent speech recognition", In EUROSPEECH-1995, 1655-1658.