Publications

In this paper, we consider the task of language identification in the context of mismatch conditions. Specifically, we address the issue of using unlabeled data in the domain of interest to improve the performance of a state-of-the-art system.

Major depressive disorder (MDD) is known to result in neurophysiological and neurocognitive changes that affect control of motor, linguistic, and cognitive functions. These changes are associated with a decline in dynamics and coordination of speech and facial motor control, while neurocognitive changes influence dialogue semantics. In this paper, biomarkers are derived from all of these modalities.

The automatic determination of emotional state from multimedia content is an inherently challenging problem with a broad range of applications including biomedical diagnostics, multimedia retrieval, and human computer interfaces. This paper provides an overview of our AVEC Emotion Challenge system, which uses multi-feature learning and fusion across all available modalities.

There have been many impressive results obtained using deep learning for emotion recognition tasks in the last few years. In this work, we present a system that performs emotion recognition on video data using both convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

I-Vector based speaker and language identification provides state of the art performance. However, this comes as a more computationally complex solution, which can often lead to challenges in resource-limited devices, such as phones or tablets. We present the implementation of an I-Vector speaker and language recognition system on the Android platform in the form of a fully functional application that allows speaker enrollment and language/speaker scoring within mobile contexts.

Effective monitoring of bulbar disease progression in persons with amyotrophic lateral sclerosis (ALS) requires rapid, objective, automatic assessment of speech loss. The purpose of this work was to identify acoustic features that aid in predicting intelligibility loss and speaking rate decline in individuals with ALS.

The epilarynx plays an important role in speech production, carrying information about the individual speaker and manner of articulation. Recent spectral processing techniques isolate a unique resonance with characteristics of the epilarynx previously shown via simulation, specifically cyclicity. Using Magnetic Resonance Imaging (MRI), the present work relates this estimated cyclic peak frequency to measured epilarynx length.

Spoken language recognition requires a series of signal processing steps and learning algorithms to model distinguishing characteristics of different languages. In this paper, we present a sparse discriminative feature learning framework for language recognition. We use sparse coding, an unsupervised method, to compute efficient representations for spectral features from a speech utterance while learning basis vectors for language models.

Recently there has been a great deal of interest in using deep neural networks (DNNs) for channel compensation under reverberant or noisy channel conditions such as those found in microphone data. This paper compares the use of real and synthetic data for training denoising DNNs for multi-microphone speaker recognition.

This paper describes the AFRL-MITLL statistical machine translation systems and the improvements that were developed during the WMT16 evaluation campaign. New techniques applied this year include Neural Machine Translation, a unique selection process for language modelling data, additional out-of-vocabulary transliteration techniques, and morphology generation.