5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Towards Speech Understanding Across Multiple Languages

Todd Ward (1), Salim Roukos (1), Chalapathy Neti (1), Jerome Gros (2), Mark Epstein (1), Satya Dharanipragada (1)

(1) IBM, USA
(2) IBM (formerly of), USA

In this paper we describe our initial efforts in building a natural language understanding (NLU) system across multiple languages. The system allows users to switch languages seamlessly in a single session without requiring any switch in the speech recognition system. Context-dependence is maintained across utterances, even when the user changes languages. Towards this end we have begun building a universal speech recognizer for English and French languages. We experiment with a common phonology for both French and English with a novel mechanism to handle language dependent variations. Our best results so far show about 5% relative performance degradation for English relative to a unilingual English system and a 9% relative degradation in French relative to a unilingual French system. The NLU system uses the same statistical understanding algorithms for each language, making system development, maintenance and portability vastly superior to systems built customly for each language.

Full Paper

Bibliographic reference.  Ward, Todd / Roukos, Salim / Neti, Chalapathy / Gros, Jerome / Epstein, Mark / Dharanipragada, Satya (1998): "Towards speech understanding across multiple languages", In ICSLP-1998, paper 0400.