Abstract Humans can describe observations and act upon requests.  This requires that language be grounded in perception and motor control.  I will present several components of my long-term research program to understand the vision-language-motor interface[…]

Read More

Abstract When considering building speech recognition and keyword search (KWS) systems for a ‘new’ language, two key questions are “how much data is going to be needed?” and “what resources are available?”. This talk will look[…]

Read More

Abstract In this study, we present a deep mixture of experts (DMoE) neural-network architecture for single microphone speech enhancement. By contrast to many speech enhancement algorithms that overlook the spectral variability of the speech signal,[…]

Read More

Abstract The finance industry increasingly seeks insight from unstructured data, including through text analytics. In this talk, I will give a brief survey of NLP as used in text analytics, then talk in detail about[…]

Read More

Abstract We all turn towards Wikipedia with questions we want to know more about, but eventually find ourselves on the limit of its coverage. Instead of providing “ten blue links” as common in Web search,[…]

Read More

Abstract Understanding attention is key to many auditory tasks. In this talk I would like to summarize several aspects of attention that we have used to better understand how humans use attention in our daily lives.[…]

Read More

Abstract Neural architectures for machine translation and language modeling is an active research field. The first part of this talk introduces several architectural changes to the original work of Bahdanau et al. 2014. We replace[…]

Read More