FOS: Fwd: Will Styler Colloquium (9/28)- B342 Wells Hall

[Suzanne Evans Wagner]

---------- Forwarded message ---------
From: smit2297 <smit2297 at msu.edu>
Date: Tue, Sep 26, 2017 at 11:08 AM
Subject: Will Styler Colloquium (9/28)- B342 Wells Hall
To: lin-grad at lin.msu.edu <lin-grad at lin.msu.edu>


Hi everyone,


This is a reminder that there is a colloquium this Thursday, September
28th at 4:30pm, in B342 Wells Hall. Our speaker is Will Styler from the
University of Michigan, and his talk is titled "Ask an Algorithm: Using
Machine Learning to Study Human Speech" (abstract below). We will have a
coffee reception at 4PM and will go to Sindhu for dinner afterwards. We
hope to see you there!


Sincerely,
Kaylin and Scott
MSU Linguistics Colloquium Co-Chairs
smit2297 at msu.edu; nelso672 at msu.edu


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

Ask an Algorithm: Using Machine Learning to study Human Speech
Will Styler (University of Michigan)

Machine learning, the use of nuanced computer models to analyze and predict
data, has a long history in speech recognition and natural language
processing, but have largely been limited to more applied, engineering
tasks.  This talk will describe two more research-focused applications of
machine learning in the study of speech perception and production.

For speech perception, we'll examine the difficult problem of identifying
acoustic cues to a complex phonetic contrast, in this case, vowel
nasality.  Here, by training machine learning algorithms on acoustic
measurements, we can more directly measure the informativeness of the
various acoustic features to the contrast.  This by-feature informativeness
data was then used to create hypotheses about human cue usage, and then, to
model the observed human patterns of perception, showing that these models
were able to predict not only the utilized cue, but the subtle patterns of
perception arising from less informative changes.

For speech production, we'll focus on data from Electromagnetic
Articulography (EMA), which provides position data for the articulators
with high temporal and spatial resolution, and discuss our ongoing efforts
to identify and characterize pause postures (specific vocal tract
configurations at prosodic boundaries, c.f. Katsika et al. 2014) in the
speech of 7 speakers of American English.  Here, the lip aperture
trajectories of 800+ individual pauses were gold-standard annotated by a
member of the research team, and then subjected to principal component
analysis.  These analyses were then used to train a support vector machine
(SVM) classifier, which achieved a 96% classification accuracy in
cross-validation tests, with a Cohen's Kappa showing machine-to-annotator
agreement of 0.79, suggesting the potential for improvements in speed,
consistency, and objective characterization of gestures.

These methods of modeling feature importance and classifying curves using
machine learning both demonstrate concrete methods which are potentially
useful and applicable to a variety of questions in phonetics, and
potentially, in linguistics in general.


_______________________________________________
lin-grad mailing list
lin-grad at lin.msu.edu
http://mailman.egr.msu.edu/mailman/listinfo/lin-grad
-- 
Suzanne Evans Wagner
Associate Professor of Linguistics
B-401 Wells Hall
Department of Linguistics and Languages
Michigan State University
East Lansing, MI 48824

Tel: +1 (517) 355-9739
http://www.msu.edu/~wagnersu
sociolinguistics.linglang.msu.edu

Office hours: http://swagner.youcanbook.me

Associate editor, Linguistics Vanguard
<http://www.degruyter.com/view/j/lingvan>
Co-editor, *Routledge Studies in Language Change
<http://www.routledge.com/books/series/RSLC/>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.egr.msu.edu/mailman/public/fos/attachments/20170926/a99bc7c9/attachment.html>