[Theory] REMINDER: 8/12 Talks at TTIC: Hung-yi Lee, National Taiwan University

Mary Marre mmarre at ttic.edu
Thu Aug 11 13:24:21 CDT 2022


*When:*        Friday, August 12th at* 1:30 pm CT*


*Where:       *Talk will be given *live, in-person* at

                   TTIC, 6045 S. Kenwood Avenue

                   5th Floor, Room 530

*Virtually:*  via Panopto (*livestream*
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e1bef456-5061-49f6-bf5e-aee9010924ab>
)

*Who: *         Hung-yi Lee, National Taiwan University


------------------------------

*Title:*   Recent Progress of Self-supervised Learning for Speech Processing

*Abstract: *Self-supervised learning (SSL) has shown to be vital for
advancing research in natural language processing (NLP), computer vision
(CV), and speech processing. The paradigm pre-trains a shared model on
large volumes of unlabeled data and achieves state-of-the-art for various
tasks with minimal adaptation. Then this talk will share the recent
advances and findings on SSL models for speech processing done at 2022
Eighth Frederick Jelinek Memorial Summer Workshop (JSALT). I'll start by
discussing how to train a better SSL model, including compressing it,
making it more robust, and enhancing pre-training with visual information.
We then discuss efficient ways to leverage SSL models in downstream tasks,
including adapters and hints. We then talk about applying SSL models to
prosody-related tasks and unsupervised ASR, and share some possible
extended uses of unsupervised ASR. Finally, we'll share a speech SSL
toolkit.
*Bio:* Hung-yi Lee (李宏毅) is an associate professor of the Department of
Electrical Engineering of National Taiwan University (NTU), with a joint
appointment at the Department of Computer Science & Information Engineering
of the university. His recent research focuses on developing technology
that can reduce the requirement of annotated data for speech processing
(including voice conversion and speech recognition) and natural language
processing (including abstractive summarization and question answering). He
won Salesforce Research Deep Learning Grant in 2019, AWS ML Research Award
in 2020, Outstanding Young Engineer Award from The Chinese Institute of
Electrical Engineering in 2018, Young Scholar Innovation Award from
Foundation for the Advancement of Outstanding Scholarship in 2019, Ta-You
Wu Memorial Award from Ministry of Science and Technology of Taiwan in
2019, and The 59th Ten Outstanding Young Person Award in Science and
Technology Research & Development of Taiwan. He owns a YouTube channel
teaching deep learning in Mandarin with about 100k Subscribers.

*Host:* *Karen Livescu* <klivescu at ttic.edu>



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Chicago, IL  60637*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Sat, Aug 6, 2022 at 12:02 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*        Friday, August 12th at* 1:30 pm CT*
>
>
> *Where:       *Talk will be given *live, in-person* at
>
>                    TTIC, 6045 S. Kenwood Avenue
>
>                    5th Floor, Room 530
>
> *Virtually:*  via Panopto (*livestream*
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e1bef456-5061-49f6-bf5e-aee9010924ab>
> )
>
> *Who: *         Hung-yi Lee, National Taiwan University
>
>
> ------------------------------
>
> *Title:*   Recent Progress of Self-supervised Learning for Speech
> Processing
>
> *Abstract: *Self-supervised learning (SSL) has shown to be vital for
> advancing research in natural language processing (NLP), computer vision
> (CV), and speech processing. The paradigm pre-trains a shared model on
> large volumes of unlabeled data and achieves state-of-the-art for various
> tasks with minimal adaptation. Then this talk will share the recent
> advances and findings on SSL models for speech processing done at 2022
> Eighth Frederick Jelinek Memorial Summer Workshop (JSALT). I'll start by
> discussing how to train a better SSL model, including compressing it,
> making it more robust, and enhancing pre-training with visual information.
> We then discuss efficient ways to leverage SSL models in downstream tasks,
> including adapters and hints. We then talk about applying SSL models to
> prosody-related tasks and unsupervised ASR, and share some possible
> extended uses of unsupervised ASR. Finally, we'll share a speech SSL
> toolkit.
> *Bio:* Hung-yi Lee (李宏毅) is an associate professor of the Department of
> Electrical Engineering of National Taiwan University (NTU), with a joint
> appointment at the Department of Computer Science & Information Engineering
> of the university. His recent research focuses on developing technology
> that can reduce the requirement of annotated data for speech processing
> (including voice conversion and speech recognition) and natural language
> processing (including abstractive summarization and question answering). He
> won Salesforce Research Deep Learning Grant in 2019, AWS ML Research Award
> in 2020, Outstanding Young Engineer Award from The Chinese Institute of
> Electrical Engineering in 2018, Young Scholar Innovation Award from
> Foundation for the Advancement of Outstanding Scholarship in 2019, Ta-You
> Wu Memorial Award from Ministry of Science and Technology of Taiwan in
> 2019, and The 59th Ten Outstanding Young Person Award in Science and
> Technology Research & Development of Taiwan. He owns a YouTube channel
> teaching deep learning in Mandarin with about 100k Subscribers.
>
> *Host:* *Karen Livescu* <klivescu at ttic.edu>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Chicago, IL  60637*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220811/7d72793c/attachment.html>


More information about the Theory mailing list