Several adaptation approaches have heen proposed in an effort t,o improve the speech recognition performance in mismatched conditions. However, the application of these approaches had heen most,ly constrained to the speaker or channel adaptation tasks. In this paper, we first investigate t,he effect of mismatched dialects between training and testing speakers in an Automatic Speech Recognition (ASR) system. We find that a mismatch in dialect,s significantly influences the recognition accuracy. Consequently, we apply several adaptation approaches to develop a dialect-specific recognition system using a dialect-dependent, system trained on a different dialect and a small number of training sentences from the target dialect. We show that, adaptation improves recognition performance dramatically with small amount,s of training sentences. We further show that, although the recognition performance of traditionally trained systems highly degrades as we decrease the number of training speakers, the performance of adapted systsems is not influenced so much.

This paper I describes a speech to speech translation system using standard components and a suite of generalizable customization techniques. The system currently translates air travel planning queries from English to Swedish. The modulax architecture is designed to be easy to port to new domains and languages, and consists of a pipelined series of processing phases. The output of each phase consists of multiple hypotheses; statistical preference mechanisms, the data for which is derived from automatic processing of domain corpora, are used between each pair of phases to filter hypotheses. Linguistic knowledge is represented throughout the system in declarative form. We summarize the architectures of the component systems and the interfaces between them, and present initial performance results.

This paper describes and evaluates a simple and general solution to the handling of compound nouns in Swedish and other languages in which compounds can be formed by concatenation of single words. The basic idea is to split compounds into their components and treat these components as recognition units equivalent to other words in the language model. By using a principled grammar-based language-processing architecture, it is then possible to accommodate input in split-compound format.

No abstract

This paper describes and evaluates a simple and general solution to the handling of compound nouns in Swedish and other languages in which compounds can be formed by concatenation of single words. The basic idea is to split compounds into their components and treat these components as recognition units equivalent to other words in the language model. By using a principled grammar-based language-processing architecture, it is then possible to accommodate input in split-compound format. 1