Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

A New Probabilistic Framework for Connectionist Time Alignment

Patrick Haffner

France Telecom, Centre National d'Etudes des Telecommunications, CNET/LAA/TSS/RCP, Lannion, France

To build optimally effective word classifiers, one research direction in speech recognition is to train a connectionist architecture with a gradient back-propagation procedure that minimises the word error rate directly. The first step was the integration of the DTW alignment procedure into the architecture: the Multi-State Time Delay Neural Network (MS-TDNN[6]) architecture was successfully demonstrated on several large speech recognition tasks. In this paper, we provide an HMM probabilistic framework for the alignment procedure, with improved experimental results. Moreover, applying a unified HMM/connectionist formalation to global speech recognition systems suggests ways to exchange expertise between both fields.

Full Paper

Bibliographic reference.  Haffner, Patrick (1994): "A new probabilistic framework for connectionist time alignment", In ICSLP-1994, 1559-1562.