4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Hierarchical Partition of the Articulatory State Space for Overlapping-feature Based Speech Recognition

Li Deng (1), Jim Jian-Xiong Wu (1,2)

(1) Department of Electrical and Computer Engineering, University of Waterloo, Ontario, Canada
(2) Nortel Technology, Nuns’ Island, Verdun, Québec, Canada

We describe our recent work on improving an overlapping articulatory feature (sub-phonemic) based speech recognizer with robustness to the requirement of training data. A new decision-tree algorithm is developed and applied to the recognizer design which results in hierarchical partitioning of the articulatory state space. The articulatory states associated with common acoustic correlates, a phenomenon caused by the many-to-one articulation-to-acoustics mapping well known in speech production, are automatically clustered by the decision-tree algorithm. This enables effective prediction of the unseen articulatory states in the training, thereby increasing the recognizer’s robustness. Some preliminary experimental results are provided.

Full Paper

Bibliographic reference.  Deng, Li / Wu, Jim Jian-Xiong (1996): "Hierarchical partition of the articulatory state space for overlapping-feature based speech recognition", In ICSLP-1996, 2266-2269.