Speech & natural language publications

We explore interfaces for presenting this information to users after a meeting is completed, using two post-meeting interfaces that display information from topics and action items respectively.

We describe a generic set of tools for representing, annotating, and analysing multi-party discourse, including: an ontology of multimodal discourse, a programming interface for that ontology, and NOMOS – a flexible and…

We present a survey of the state of the art in voice-based speaker identification research. We describe the general framework of a text-independent speaker verification system, and, as an example,…

We introduce a multi-stage ensemble framework, Error-Driven Generalist+ Expert or Edge, for improved classification on large-scale text categorization problems.

We propose a new method for detecting out-of-vocabulary (OOV) words for large vocabulary continuous speech recognition (LVCSR) systems. Our method is based on performing a joint alignment between independently generated…

We present a sentence extraction algorithm for Information Distillation, a task where for a given templated query, relevant passages must be extracted from massive audio and textual document sources.

We explore the use of morph-based language models in large-vocabulary continuous speech recognition systems across four so-called “morphologically rich” languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. The morphs are…

In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system.

We describe a highly accurate large-vocabulary continuous Mandarin speech recognizer, a collaborative effort among four research organizations. Particularly, we build two acoustic models (AMs) with significant differences but with similar…

In this paper, we present a study – conducted in the context of the Halo Project – cataloging the types of failures that occur when capturing knowledge from natural language.

As part of the ongoing project, Project Halo, our goal is to build a system capable of answering questions posed by novice users to a formal knowledge base. In our…

We propose three methods for extending the Boosting family of classifiers motivated by the real-life problems we have encountered. Our results indicate that it is possible to obtain the same…