5th International Conference on Spoken Language Processing
This paper describes two related systems which provide frameworks for encoding linguistic knowledge into formal rules within the context of a trainable probabilistic model. The first system, TINA, drives top-down from sentence level structure, terminating in either words or syllables. It's main purpose is to provide a meaning representation for the sentence. The other system, ANGIE, operates bottom-up from phonetic or orthographic units, characterizing word substructure. It provides a framework for both phonological rule modelling and letter-to-sound/sound-to-letter transformations. The two systems logically converge on the syllable or word layer. We have recently been successful in integrating their combined constraint into a recognizer search, achieving considerable improvement in understanding accuracy. In this paper, I will look both toward the past and the future, identifying and motivating the decisions that were made in the design of TINA and ANGIE and the associated rule formalisms, and contemplating various remaining open research issues.
Bibliographic reference. Seneff, Stephanie (1998): "The use of linguistic hierarchies in speech understanding", In ICSLP-1998, paper 0012.