No abstract

In this paper, we e v aluate multi-Gaussian HMM systems and hybrid HMM/ANN systems in the framework of task independent training for small size (75 words) and medium size (600 words) vocabularies. To d o t h i s , we use the Phonebook database 6] which is particularly well suited to this kind of experiments since (1) it is a very large telephone database and (2) the size and content of the test vocabulary is very exible. For each system, di erent HMM topologies are compared to test the in uence of state tying (with a number of parameters approximately kept constant) on the recognition performance. Two lexica (Phonebook and CMU) are also compared and it is shown that the CMU lexicon is leading to signi cantly better performance. Finally, it is shown that with a quite simple system and a few adaptations to the basic HMM/ANN scheme, recognition performance of 98.5% and 94.7% can easily be achieved, respectively on a lexicon of 75 and 600 words (isolated words, telephone speech and lexicon words not present in the training data).

No abstract

No abstract

This paper describes the research underway for the ES-PRIT WERNICKE project. The project brings together a n umber of di erent groups from Europe and the US and focuses on extending the state-of-the-art for hybrid hidden Markov model/connectionist approaches to large vocabulary, continuous speech recognition. This paper describes the speci c goals of the research and presents the work performed to date. Results are reported for the resource management t a l k er-independent recognition task. The paper concludes with a discussion of the projected future work.