next up previous contents
Next: OBJECTIVESINDUSTRIAL RELEVANCE Up: No Title Previous: Contents

SUMMARY

 

The goal of the proposed project is to further improve the current state-of-the-art in continuous speech recognition using Artificial Neural Network (ANN) and Hidden Markov Model (HMM) approaches. Pursuing the theoretical and development work successfully carried out under the WERNICKE project (ESPRIT Basic Research Project 6487, October 1992-October 1995), this new project, referred to as SPRACH ( SPeech Recognition Algorithms for Connectionist Hybrids), will extend the research to robust and flexible speech recognition systems that can easily be adapted to new languages and new domains with new lexica and new syntaxes.

In WERNICKE, on top of substantial theoretical results, it was demonstrated, using standard international reference databases (such as the unlimited vocabulary ARPA North American Business News database, and the EU funded SQALE projectgif), that the hybrid HMM/ANN approaches lead to competitive state-of-the-art speech recognizers. Furthermore, the investigated hybrid approach was shown to have additional advantages in terms of CPU utilization and memory bandwidth. These conclusions have been confirmed by many different independent sources (see Section 1.2 for references).

While building on the WERNICKE large vocabulary continuous speech recognition system, SPRACH will also investigate the development of flexible systems for smaller, task independent applications, in different languages (UK English, French and Portuguese).

The industrial relevance of this project is high, and many useful results are expected. Firstly, it is clear that speech processing, and speech recognition in particular, will play a major role in the future multimedia and telematics applications. In this respect, while SPRACH is fully exploiting the promising HMM/ANN technology, it also addresses most of the relevant issues of speech recognition in general, such as language and lexicon modeling, application domain adaptation, and prototype development. Secondly, on top of its obvious relevance to the speech recognition technology, it is also important to note that, motivated by the results achieved in WERNICKE, these hybrid systems have already been adopted by several industries and laboratories in many different areas (see Section 1.2 for references).

To reinforce the industrial relevance of this project and its possible industrial impact, a SPRACH Industrial Advisory Board including BBC (UK), CSELT (I), Daimler-Benz (D) and Thomson (F) has been set up (see Section 1.3 and Appendix B.2 for more information about this).

Keywords: speech recognition, hidden Markov models (HMM), artificial neural networks (ANN), statistical inference in ANNs, hybrid HMM/ANN technology, language models, application domain adaptation, neural network hardware and software, speech recognition applications.

REACTIVE LONG TERM RESEARCH PROJECT

SPeech Recognition Algorithms for Connectionist Hybrids

(SPRACH) -- Ref. 20077

PART 2: Scientific and Technical Content



next up previous contents
Next: OBJECTIVESINDUSTRIAL RELEVANCE Up: No Title Previous: Contents



Jean-Marc Boite
Mon Dec 9 18:18:02 MET 1996