5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Rescoring Multiple Pronunciations Generated from Spelled Words

Roland Kuhn, Jean-Claude Junqua, Philip D. Martzen

Panasonic Technologies Inc., Speech Technology Laboratory, USA

Building on earlier work, we show how a set of binary decision trees can be trained to generate an ordered list of possible pronunciations from a spelled word. Training is carried out on a database consisting of spelled words paired with their pronunciations (in a particular language). We show how phonotactic information can be learned by a second set of decision trees, which reorder the multiple pronunciations generated by the first set. The paper defines the ``inclusion'' metric for scoring phoneticizers that generate multiple pronunciations. Experimental results employing this metric indicate that phonotactic reordering yields a slight improvement when only the top pronunciation is retained, and a large improvement when more than one hypothesis is retained. Isolated-word recognition results which show good performance for automatically-generated pronunciations are given.

Full Paper

Bibliographic reference.  Kuhn, Roland / Junqua, Jean-Claude / Martzen, Philip D. (1998): "Rescoring multiple pronunciations generated from spelled words", In ICSLP-1998, paper 0304.