Marianne Santaholma

Evaluating Task Performance for a Unidirectional Controlled Language Medical Speech Translation System

We present a task-level evaluation of the French to English version of MedSLT, a medium-vocabulary unidirectional controlled language medical speech translation system designed for doctor-patient diagnosis interviews. Our main goal was to establish task performance levels of novice users and compare them to expert users. Tests were carried out on eight medical students with no previous exposure to the system, with each student using the system for a total of three sessions. By the end of the third session, all the students were able to use the system confidently, with an average task completion time of about 4 minutes.

A Bidirectional Grammar-Based Medical Speech Translator

We describe a bidirectional version of the grammar-based MedSLT medical speech system. The system supports simple medical examination dialogues about throat pain between an English-speaking physician and a Spanish-speaking patient. The physicians side of the dialogue is assumed to consist mostly of WH-questions, and the patients of elliptical answers. The paper focusses on the grammar-based speech processing architecture, the ellipsis resolution mechanism, and the online help system.

Japanese Speech Understanding using Grammar Specialization

The most common speech understanding architecture for spoken dialogue systems is a combination of speech recognition based on a class N-gram language model, and robust parsing. For many types of applications, however, grammar-based recognition can offer concrete advantages. Training a good class N-gram language model requires substantial quantities of corpus data, which is generally not available at the start of a new project. Head-to-head comparisons of class N-gram/robust and grammar-based systems also suggest that users who are familiar with system coverage get better results from grammar-based architectures (Knight et al., 2001). As a consequence, deployed spoken dialogue systems for real-world applications frequently use grammar-based methods. This is particularly the case for speech translation systems. Although leading research systems like Verbmobil and NE-SPOLE! (Wahlster, 2000; Lavie et al., 2001) usually employ complex architectures combining statistical and rule-based methods, successful practical examples like Phraselator and S-MINDS (Phraselator, 2005; Sehda, 2005) are typically phrasal translators with grammar-based recognizers.

MedSLT: A Limited-Domain Unidirectional Grammar-Based Medical Speech Translator

MedSLT is a unidirectional medical speech translation system intended for use in doctor-patient diagnosis dialogues, which provides coverage of several different language pairs and subdomains. Vocabulary ranges from about 350 to 1000 surface words, depending on the language and subdomain. We will demo both the system itself and the development environment, which uses a combination of rule-based and data-driven methods to construct efficient recognisers, generators and transfer rule sets from small corpora.

A Development Environment for Building Grammar-Based Speech-Enabled Applications

We present a development environment for Regulus, a toolkit for building unification grammar-based speech-enabled systems, focussing on new functionality added over the last year. In particular, we will show an initial version of a GUI-based top-level for the development environment, a tool that supports graphical debugging of unification grammars by cutting and pasting of derivation trees, and various functionalities that support systematic development of speech translation and spoken dialogue applications built using Regulus.

Making Speech Look Like Text in the Regulus Development Environment

We present an overview of the development environment for Regulus, an Open Source platform for construction of grammar-based speech-enabled systems, focussing on recent work whose goal has been to introduce uniformity between text and speech views of Regulus-based applications. We argue the advantages of being able to switch quickly between text and speech modalities in interactive and offline testing, and describe how the new functionalities enable rapid prototyping of spoken dialogue systems and speech translators.