Speech & natural language publications

In this study, our first objective was to improve the characterization of connected speech production in each variant of primary progressive aphasia, by quantifying speech output along a number of…

In this study, as part of a larger scale multiparty meeting understanding system, we analyze various methods for adapting dialog act segmentation and tagging models trained on conversational telephone speech…

We investigate usefulness of across-phone variability for speaker recognition in a joint factor analysis (JFA) framework. We estimate the variability as across-phone covariance within a conversation side averaged over all…

We examine the impact of disfluencies from broadcast conversation data on our hierarchical phrase-based SMT system and implement automatic disfluency removal approaches for cleansing the MT input.

This study explores speaker-specific modeling for the task of automatic segmentation of speech into dialog acts (DAs), using a linear combination of speaker-dependent and speaker-independent language and prosodic models.

We propose a new JFA scoring method that is both symmetrical and efficient.

We propose a framework for employing both speech/non-speech-based (“contextual”) features and prosodic features, and apply it to DA segmentation and classification in multiparty meetings.

In this work, we study the two modeling techniques for the simpler set of features. We show that, for these features, a combination of JFA systems for different sequence lengths…

We investigate the use of hierarchical Gaussian shortlists to speed up Gaussian likelihood computation.

The goal of this work was to explore the optimization of the feature extraction module (front-end) parameters to improve bird species recognition.

This work investigates the application of multi-view semi-supervised learning algorithms on the sentence boundary classification problem by using lexical and prosodic information.

We propose a novel approach to modeling prosodic features.