<div dir="ltr"><div dir="ltr"><div class="gmail_default" style="font-size:small"><div><b>When</b>: Wednesday, December 7th from <b style="background-color:rgb(255,255,0)">1:00 - 3:00 pm CT</b><br><br><b>Virtually</b>: attend virtually <b><font color="#0000ff"><a href="https://uchicagogroup.zoom.us/meeting/register/tJYodemsrzwjHdZUCfy-hT3ul111h5LP-JIO" target="_blank">here</a></font></b><br></div><div><br><b>Who</b>: <font face="arial, sans-serif">Qingming Tang, TTIC</font></div><div><br></div><div><div class="MsoNormal" align="center" style="margin:0in 0in 8pt;text-align:center;line-height:15.6933px;font-size:11pt;font-family:Calibri,sans-serif"><hr size="2" width="100%" align="center"></div><br><b>Thesis Title</b>: <font face="arial, sans-serif"><b> </b>Representation Learning for Speech Data</font><br><br><b>Abstract</b>: Supervised learning has been the dominant approach for training deep neural networks for learning good representations. However, one limiting factor to scale supervised learning is the lack of enough annotated data. Motivated by this challenge, it is natural to explore methods that learn generic information from a large amount of unlabeled data. I describe the broad study of representation learning for speech data I have conducted. Unlike most other works that focus on one or a few learning settings, this thesis studies multiple settings: supervised learning with auxiliary losses, unsupervised learning, semi-supervised learning, and multi-view learning. Besides different learning problems, I also explore multiple approaches for representation learning. For example, I will present our bidirectional contextual encoder for learning speech representations (introduced in 2018), using informative prior distributions to assist autoencoding-style representation learning, a few techniques for variational representation learning models, and multi-view masked reconstruction for self-supervised learning.</div><div><br></div><div><b>Thesis Advisor</b>: <a href="mailto:klivescu@ttic.edu" target="_blank"><b>Karen Livescu</b></a> </div><div><br></div><div><br></div><div><br></div><div><br></div><div><br></div></div><div><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><span style="font-family:arial,helvetica,sans-serif;font-size:x-small">Mary C. Marre</span><br></div><div><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue, Rm 517</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">773-834-1757</font></i></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Dec 6, 2022 at 3:06 PM Mary Marre <<a href="mailto:mmarre@ttic.edu">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div dir="ltr"><div style="font-size:small"><div><b>When</b>: Wednesday, December 7th from <b style="background-color:rgb(255,255,0)">1:00 - 3:00 pm CT</b><br><br><b>Virtually</b>: attend virtually <b><font color="#0000ff"><a href="https://uchicagogroup.zoom.us/meeting/register/tJYodemsrzwjHdZUCfy-hT3ul111h5LP-JIO" target="_blank">here</a></font></b><br></div><div><br><b>Who</b>: <font face="arial, sans-serif">Qingming Tang, TTIC</font></div><div><br></div><div><div class="MsoNormal" align="center" style="margin:0in 0in 8pt;text-align:center;line-height:15.6933px;font-size:11pt;font-family:Calibri,sans-serif"><hr size="2" width="100%" align="center"></div><br><b><span>Thesis</span> Title</b>: <font face="arial, sans-serif"><b> </b>Representation Learning for Speech Data</font><br><br><b>Abstract</b>: Supervised learning has been the dominant approach for training deep neural networks for learning good representations. However, one limiting factor to scale supervised learning is the lack of enough annotated data. Motivated by this challenge, it is natural to explore methods that learn generic information from a large amount of unlabeled data. I describe the broad study of representation learning for speech data I have conducted. Unlike most other works that focus on one or a few learning settings, this <span>thesis</span> studies multiple settings: supervised learning with auxiliary losses, unsupervised learning, semi-supervised learning, and multi-view learning. Besides different learning problems, I also explore multiple approaches for representation learning. For example, I will present our bidirectional contextual encoder for learning speech representations (introduced in 2018), using informative prior distributions to assist autoencoding-style representation learning, a few techniques for variational representation learning models, and multi-view masked reconstruction for self-supervised learning.</div><div><br></div><div><b><span>Thesis</span> Advisor</b>: <a href="mailto:klivescu@ttic.edu" target="_blank"><b>Karen Livescu</b></a> </div><div><br></div><div><br></div><div><br></div><div><br></div></div><div><div dir="ltr"><div dir="ltr"><div><span style="font-family:arial,helvetica,sans-serif;font-size:x-small">Mary C. Marre</span><br></div><div><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue, Rm 517</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">773-834-1757</font></i></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Nov 30, 2022 at 10:41 AM Mary Marre <<a href="mailto:mmarre@ttic.edu" target="_blank">mmarre@ttic.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div><div style="font-size:small"><b>When</b>: Wednesday, December 7th from <b style="background-color:rgb(255,255,0)">1:00 - 3:00 pm CT</b><br><br><b>Virtually</b>: attend virtually <b><font color="#0000ff"><a href="https://uchicagogroup.zoom.us/meeting/register/tJYodemsrzwjHdZUCfy-hT3ul111h5LP-JIO" target="_blank">here</a></font></b><br></div><div><br><b style="font-size:small">Who</b>: <font face="arial, sans-serif">Qingming Tan, TTIC</font></div><div><br></div><div><div class="MsoNormal" align="center" style="text-align:center;margin:0in 0in 8pt;line-height:107%;font-size:11pt;font-family:Calibri,sans-serif">
<hr size="2" width="100%" align="center">
</div><br><b style="font-size:small"><span>Thesis</span> Title</b>:
<font face="arial, sans-serif"><b> </b>Representation Learning for Speech Data</font><br><br><b style="font-size:small">Abstract</b>: Supervised learning has been the dominant approach for training deep neural networks for learning good representations. However, one limiting factor to scale supervised learning is the lack of enough annotated data. Motivated by this challenge, it is natural to explore methods that learn generic information from a large amount of unlabeled data. I describe the broad study of representation learning for speech data I have conducted. Unlike most other works that focus on one or a few learning settings, this thesis studies multiple settings: supervised learning with auxiliary losses, unsupervised learning, semi-supervised learning, and multi-view learning. Besides different learning problems, I also explore multiple approaches for representation learning. For example, I will present our bidirectional contextual encoder for learning speech representations (introduced in 2018), using informative prior distributions to assist autoencoding-style representation learning, a few techniques for variational representation learning models, and multi-view masked reconstruction for self-supervised learning.</div><div style="font-size:small"><br></div><div style="font-size:small"><b><span>Thesis</span> Advisor</b>: <a href="mailto:klivescu@ttic.edu" target="_blank"><b>Karen Livescu</b></a> </div><div style="font-size:small"><br></div><div style="font-size:small"><br></div><div style="font-size:small"><br></div></div><div><div dir="ltr"><div dir="ltr"><div><span style="font-family:arial,helvetica,sans-serif;font-size:x-small">Mary C. Marre</span><br></div><div><div><font face="arial, helvetica, sans-serif" size="1">Faculty Administrative Support</font></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1"><b>Toyota Technological Institute</b></font></i></div><div><i><font face="arial, helvetica, sans-serif" color="#3d85c6" size="1">6045 S. Kenwood Avenue, Rm 517</font></i></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">Chicago, IL 60637</font></i><br></font></div><div><font size="1"><i><font face="arial, helvetica, sans-serif" color="#3d85c6">773-834-1757</font></i></font></div><div><b><i><a href="mailto:mmarre@ttic.edu" target="_blank"><font face="arial, helvetica, sans-serif" size="1">mmarre@ttic.edu</font></a></i></b></div></div></div></div></div></div>
</blockquote></div></div>
</blockquote></div></div>