Speech & natural language publications

We evaluate existing automatic speech-recognition (ASR) systems to measure their performance in interpreting spoken clinical questions and to adapt one ASR system to improve its performance on this task.

We present Conditional Random Fields based approaches for detecting agreement/disagreement between speakers in English broadcast conversation shows.

We develop language-independent (LI) versions of constraints and compare results to parallel LD versions for English data on the NIST 2008 interview task.

In this paper, we show that performance can be significantly improved with the use of probabilistic linear discriminant analysis (PLDA) for session variability compensation. 

In this paper we investigate how these two approaches compare for state-of-the-art recognition systems applied to meeting data from the two most recent NIST Rich Transcription evaluations.  Our results show…

We propose to include synchrony effects, known to exist in the auditory system, to represent voiced parts of the speech signal in a robust way. 

The goal of this work was to explore modeling techniques to improve bird species classification from audio samples.

In this work, we compare several known approaches for multilingual acoustic modeling for three languages, Dari, Farsi and Pashto, which are of recent geo-political interest.

This article reviews the physical and psychoacoustic foundations, practical methods, and engineering challenges to the realization of motion-tracked sound over headphones.

We describe experiments on a modest-sized corpus of regulation annotated with a novel variant of logical form, called abstract syntax trees (ASTs).

In this paper, I present results from a word recognition and a phone recognition experiments in noise that uses two sets of articulatory representation: continuous (tract variable trajectories) and discrete (articulatory gestures) along with…