Speech & natural language publications

We describe the systems submitted by SRI International and the University of the Basque Country for the Semantic Textual Similarity SemEval-2012 task.

We present a Dynamic Bayesian Network based speech recognition architecture that models the articulatory gestures as hidden variables and uses them for speech recognition. 

We introduce a new database for evaluation of speaker recognition systems. 

We review developments in the SRI Language Modeling Toolkit (SRILM) since 2002, when a previous paper on SRILM was published.

This paper presents models for detecting agreement/disagreement between speakers in English and Arabic broadcast conversation shows.

In this study, we focus on speech features that can identify the speaker’s emotional health, i.e., whether the speaker is depressed or not. 

We study constrained speaker recognition systems, or systems that model standard cepstral features that fall within particular types of speech regions. 

We present models for detecting various attributes of a speaker based on uttered text alone.

The purpose of this work is to show how recent developments in cepstral-based systems for speaker recognition can be leveraged for the use of Maximum Likelihood Linear Regression (MLLR) transforms. 

We study the effectiveness of recently developed language recognition techniques based on speech recognition models for the discrimination of Arabic dialects.

In this paper we apply the promising iVector extraction technique followed by PLDA modeling to simple prosodic contour features.