The HIMARNNET project

[ FPMs > TCTS > ASR group > Projects > HIMARNNET ]

[Partners]

[Abstract] 

HIdden MARkov models and Neural NETworks (1993-1995)

ESPRIT Long Term Research RTD Project Ref. 6488.

Partners

• Faculté Polytechnique de Mons (Belgium)

• ASCOM Holding Ltd (Switzerland)

• École Polytechnique Federale de Lausanne (Switzerland)

• Lernout & Hauspie Speech Products (Belgium)

• Tedas Gesellschaft für Technische Datenverarbeitung mbH (Germany).

Abstract

The development and assessment of neural network techniques for improving the robustness of medium vocabulary (50-100 words), speaker-independent, isolated word recognisers for telephone transmission quality speech. The dominant technology is Hidden Markov Models (HMMs) but this has significant limitations, some of which could be alleviated by the judicious use of artificial neural networks (ANNs) or hybrid combinations of both techniques. Direct comparisons of ANN-based, HMM-based, and hybrid ANN/HMM techniques for speech recognition will be made. The developments will be integrated and validated in the context of a telephone application including speech recognition capabilities. A number of prototypes have been demonstrated on low cost commodity systems. The telephone application developed within the project will be the basis for product development by Tedas.