Improving speech embedding using crossmodal transfer learning with audio-visual data
Related publications (41)
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The chapter is based on new empirical data collected through primary surveys and in-depth interviews with Indian skilled migrants in Europe and with returnees in India. The study found that Indian skilled professionals, scientists and students are contribu ...
Imaging systems can be designed using examples and methods similar to the techniques used in deep learning. We describe experimental results demonstrating optical tomography based on the learning approach. ...
Knowledge is getting increasingly more complex. Learners, from Kindergarten to higher education, require powerful tools to connect complex ideas. This paper explores the range of studies that investigated concept maps as learning, metacognitive, collaborat ...
Social technologies are leading to transformations in education, by empowering the way learners connect to each other, by introducing new means for teaching and learning and by reshaping the way knowledge is delivered. Annotating texts is a learning strate ...
The present paper addresses an advanced teaching lab consisting of setting up an islanded production unit. This teaching lab takes place in the very last semester at master level for students in electrical engineering with energy specialization. The purpos ...
Open ended learning is a dynamic process based on the continuous analysis of new data, guided by past experience. On one side it is helpful to take advantage of prior knowledge when only few information on a new task is available (transfer learning). On th ...
This paper introduces a method to predict and analyse students' mathematical performance by detecting distinguishable subgroups of children who share similar learning patterns. We employ pairwise clustering to analyse a comprehensive dataset of user intera ...
With the general technological advances of the recent years, current learning environments amass an abundance of data. Albeit such data offer the chance of better understand the learning process, stakeholders – learners, teachers and institutions – often n ...
Many students leave school with a fragmented understanding of biology that does not allow them to connect their ideas to their everyday lives (Wandersee, 1989; Mintzes, Wandersee, & Novak, 1998; Mintzes, Wandersee, & Novak, 2000a). Understanding evolution ...
In this paper we introduce a budgeted knowledge transfer algorithm for non-homogeneous reinforcement learning agents. Here the source and the target agents are completely identical except in their state representations. The algorithm uses functional space ...