CLSP Townhall/Welcome New Students
August 11, 2021
When:
September 13, 2021 @ 12:00 pm – 1:15 pm
Where:
Maryland Hall 110, 3400 N. Charles Street, Baltimore, MD 21218
Events
Alicia Lozano-Diez (Universidad Autonoma de Madrid) “Text-Dependent Speaker Verification: BUT system for the SdSV Challenge 2020”
February 9, 2021
When:
March 12, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract Speaker verification (SV) is particularly challenging when the audio recordings are short in duration. Aiming at this, the Short-duration Speaker Verification (SdSV) challenge was organized in 2020, providing a framework for the evaluation of[…]
Carolina Parada (Google AI) “State of Robotics @ Google”
January 22, 2021
When:
April 23, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract Robotics@Google’s mission is to make robots useful in the real world through machine learning. We are excited about a new model for robotics, designed for generalization across diverse environments and instructions. This model is[…]
Wilker Aziz (University of Amsterdam) “The Inadequacy of the Mode in Neural Machine Translation”
January 22, 2021
When:
April 19, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract Neural sequence generation systems oftentimes generate sequences by searching for the most likely sequence under the learnt probability distribution. This assumes that the most likely sequence, i.e. the mode, under such a model must[…]
Jiri Mekyska (Brno University of Technology) “Data Science in Small Medical Data Sets: From Logistic Regression Towards Logistic Regression”
January 22, 2021
When:
March 29, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract Data science in small medical datasets usually means doing precision guesswork on unreliable data provided by those with high expectations. The first part of this talk will focus on issues that data scientists and[…]
Shannon Heald (University of Chicago)“Speech Recognition in the Context of Variability: Lessons from Human Listeners”
January 22, 2021
When:
March 15, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract There is a tremendous amount of variation in the acoustic properties of speech categories. A well-known example of this is the acoustic-phonetic variability found between talkers: different talkers will use the same acoustic pattern[…]
Tuo Zhao (Georgia Tech) “Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach”
January 22, 2021
When:
February 26, 2021 @ 12:00 pm – 1:15 pm
Where:
via Zoom
Abstract Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is[…]
