Office hours (Week of April 30)

1 maio 2018, 11:21 • Isabel Maria Martins Trancoso

Wednesday - May 2 - 11h00-12h00 (INESC-ID)
Thursday - May 3 - 08h30-10h20 (INESC-ID)

Test 2 and Lab 3 Deadlines - NEW DEADLINE

24 abril 2018, 19:54 • Isabel Maria Martins Trancoso

Please register for Test 2 (Deadline: 29/04/2018).

Lab 3 (including part 2) should be submitted by 06/05/2018. --> 09/05/2018

Lecture - Helena Moniz - May 19th 2018 - The role of prosodic info in speech analytics and speech synthesis,

12 abril 2018, 11:30 • Isabel Maria Martins Trancoso

Bio:
Helena Moniz graduated in Modern Languages and Literature – Portuguese Studies, at Faculty of Letters, University of Lisbon (FLUL), in 1998. She took a Teacher Training graduation course in 2000, also at FLUL. She was a high school teacher from 2000 to 2006. She received a Master’s degree in Linguistics at FLUL, in 2007, and a PhD in Linguistics at FLUL in cooperation with the Technical University of Lisbon (IST), in 2013. She has been working at INESC-ID since 2000, in several national and international projects involving multidisciplinary teams of linguists and speech processing engineers. Recently, she has embraced the challenge topic of Scalable Quality Processes on Post-edition Crowdsourcing (at Unbabel).

Deadline for Lab2 and Office hours on Thursday April 12th

11 abril 2018, 13:55 • Isabel Maria Martins Trancoso

Deadline for Lab 2:  April 16th 2018
Office hours on Thursday April 12th: 11h30-12h00 (at the Lab)

Lecture - Wang Ling - April 17th 2018 - Introduction to Neural Networks

5 abril 2018, 15:23 • Isabel Maria Martins Trancoso

In this talk, I will introduce the core concepts for the understanding of neural networks. I will start from very basic concepts that everyone should be familiar with, such as numbers and basic operators (addition, subtraction and multiplication), and systematically guide the audience towards every essential concept for the understanding of how neural networks function. Using a simple example based on a popular educational cartoon, we will start by developing a simple linear model, in order to illustrate how to define a model and optimizer its parameters. Then, we show how more complex models can be built (e.g. Multilayer Perceptrons), and describe the key technologies that enable, such models to be built and trained (e.g. GPUs, Computational graphs).

Bio:
Wang Ling is a senior research scientist in Google DeepMind. He received his dual-degree PhD in Language Technologies in 2015 from Carnegie Mellon University and University of Lisbon. His research interests include Machine Translation, Natural Language Processing, Machine Learning and Deep Learning. He has published over 30 articles in the top tier conferences and journals (including Computational Linguistics, ACL and EMNLP).

Attendance is mandatory for the students of Speech Processing course.