Speech & natural language publications

We propose a framework for analyzing episodic conversational activities in terms of expressed relationships between the participants and utterance content.

This paper evaluates methods for building the graph, including link selection strategies, and two methods for representing input texts as distributions over the graph nodes: one based on a dictionary…

In this work, we apply JFA to a very diverse set of recording conditions and conversation modes in NIST 2008 SRE, showing that having channel matched development data will give…

In this paper, we investigate the effect of using syntax in a large-scale audio document translation task targeting broadcast news and broadcast conversations.

This paper focuses on combining answers generated by a semantic parser that produces semantic role labels (SRLs) and those generated by syntactic parser that produces function tags for answering 5-W…

In this paper, we introduce two methods for efficient selection of training data to be translated by humans. Our methods are motivated by active learning and aim to choose new…

This paper proposes a simple method of fuzzy matching between query names and phones of candidate audio segments.

This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include realtime and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item…

We study the question of how intrinsic variations (associated with the speaker rather than the recording environment) affect text-independent speaker verification performance.

In this paper we will focus on the kinds of improvements for a Farsi-to- English translation system achieved by means of algorithmic changes, adding raw, domain-unspecific resources, and unsupervised morphological…

In this paper, we present a complete analysis of the phone-based cepstral system with polynomial features. We start from a simpler system that does not use phones or states and…