[Theory] REMINDER: 11/29 TTIC Colloquium: Michael Auli, FAIR

[Mary Marre]

*When:*      Monday, November 29th, 2021 at *11:00 am CT*



*Where:*     *Zoom Virtual Talk* (*register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_OeLGwcytS46pQnaheKLXUw>*)




*Who: *       Michael Auli, FAIR


*Title:*        Speech Representation Learning with Wav2vec

*Abstract: *Despite rapid progress in the recent past, current speech
recognition systems rely heavily on labeled training data. This limits this
technology to a small fraction of languages and accents spoken around the
globe. In this talk, I will give an overview of the wav2vec project which
vastly reduced the amount of supervision required to build speech
technology. The key ingredient is self-supervised pre-training in order to
learn powerful representations of speech audio solely from unlabeled data.
The resulting models can be fine-tuned with labeled data or they can be
used to perform completely unsupervised speech recognition. Our
unsupervised approach rivals some of the best published systems trained on
960 hours of labeled data from only two years ago while using no labeled
data. This is an important step towards systems which can learn to solve
tasks without explicit supervision.

*Bio: *Michael Auli is a research scientist director at Facebook AI
Research in Menlo Park. He leads teams working on speech recognition and
NLP which resulted in projects such as wav2vec, the widely used fairseq
toolkit, the first modern convolutional seq2seq models outperforming RNNs,
and several top ranked submissions at the WMT news translation task in 2018
and 2019. Before that Michael was at Microsoft Research, where he did early
work on neural machine translation and neural dialogue modeling. During his
PhD he worked on natural language processing and parsing at the University
of Edinburgh.

http://michaelauli.github.io


*Hos**ts:* *Karen Livescu* <klivescu at ttic.edu>  and  *Kevin Gimpel*
<kgimpel at ttic.edu>


For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php


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 Mon, Nov 22, 2021 at 6:41 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:*      Monday, November 29th, 2021 at *11:00 am CT*
>
>
>
> *Where:*     *Zoom Virtual Talk* (*register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_OeLGwcytS46pQnaheKLXUw>*
> )
>
>
>
> *Who: *       Michael Auli, FAIR
>
>
> *Title:*        Speech Representation Learning with Wav2vec
>
> *Abstract: *Despite rapid progress in the recent past, current speech
> recognition systems rely heavily on labeled training data. This limits this
> technology to a small fraction of languages and accents spoken around the
> globe. In this talk, I will give an overview of the wav2vec project which
> vastly reduced the amount of supervision required to build speech
> technology. The key ingredient is self-supervised pre-training in order to
> learn powerful representations of speech audio solely from unlabeled data.
> The resulting models can be fine-tuned with labeled data or they can be
> used to perform completely unsupervised speech recognition. Our
> unsupervised approach rivals some of the best published systems trained on
> 960 hours of labeled data from only two years ago while using no labeled
> data. This is an important step towards systems which can learn to solve
> tasks without explicit supervision.
>
> *Bio: *Michael Auli is a research scientist director at Facebook AI
> Research in Menlo Park. He leads teams working on speech recognition and
> NLP which resulted in projects such as wav2vec, the widely used fairseq
> toolkit, the first modern convolutional seq2seq models outperforming RNNs,
> and several top ranked submissions at the WMT news translation task in 2018
> and 2019. Before that Michael was at Microsoft Research, where he did early
> work on neural machine translation and neural dialogue modeling. During his
> PhD he worked on natural language processing and parsing at the University
> of Edinburgh.
>
> http://michaelauli.github.io
>
>
> *Hos**ts:* *Karen Livescu* <klivescu at ttic.edu>  and  *Kevin Gimpel*
> <kgimpel at ttic.edu>
>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
> 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/20211128/6fdfb194/attachment.html>