First International Conference on Spoken Language Processing (ICSLP 90)

Kobe, Japan
November 18-22, 1990

Continuous Speech Recognition on the Resource Management Database Using Connectionist Probability Estimation

Nelson Morgan (1), C. Wooters (1), Hervé Bourlard (1,3), Michael Cohen (2)

(1) International Computer Science Institute, Berkeley, CA, USA
(2) SRI International, Menlo Park, CA, USA
(3) Philips Research Laboratory Brussels, Brussels, Belgium

Previous work has shown the ability of Multilayer Perceptrons (MLPs) to estimate emission probabilities for a Hidden Markov Model (HMM) [1][2][3][4]. The advantage to this approach is the ability to incorporate multiple sources of evidence (features, temporal context) without restrictive assumptions of distribution or statistical independence. In our earlier publications on this topic, a hybrid MLP/HMM continuous speech recognition algorithm was tested on the SPICOS German-language data base. In our recent work, we have shifted to the speaker-dependent portion of DARPA's English language Resource Management (RM) data base. Both consist of continuous utterances (sentences) and incorporate a lexicon of roughly 1000 words. Preliminary results appear to support the previously reported utility of MLP probability estimation for continuous speech recognition (at least, for the case of this simple form of HMM).

Full Paper

Bibliographic reference.  Morgan, Nelson / Wooters, C. / Bourlard, Hervé / Cohen, Michael (1990): "Continuous speech recognition on the resource management database using connectionist probability estimation", In ICSLP-1990, 1337-1340.