<div dir="ltr"><br><div class="gmail_quote"><div dir="ltr">---------- Forwarded message ---------<br>From: smit2297 <<a href="mailto:smit2297@msu.edu">smit2297@msu.edu</a>><br>Date: Tue, Sep 26, 2017 at 11:08 AM<br>Subject: Will Styler Colloquium (9/28)- B342 Wells Hall<br>To: <a href="mailto:lin-grad@lin.msu.edu">lin-grad@lin.msu.edu</a> <<a href="mailto:lin-grad@lin.msu.edu">lin-grad@lin.msu.edu</a>><br></div><br><br> <div dir="ltr"> <div id="m_8396638632795213878divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif" dir="ltr"> <p>Hi everyone,</p> <p><br> </p> <p><span>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 "<span>Ask an Algorithm: Using Machine Learning to Study Human Speech</span>" (abstract below). We will have a coffee reception at 4PM and will go to Sindhu for dinner afterwards. We hope to see you there!</span></p> <p><br> </p> <p><span style="font-size:12pt"></span></p> <div>Sincerely,<br> Kaylin and Scott<br> MSU Linguistics Colloquium Co-Chairs<br> <a href="mailto:smit2297@msu.edu" target="_blank">smit2297@msu.edu</a>; <a href="mailto:nelso672@msu.edu" target="_blank">nelso672@msu.edu</a><br> <br> <br> ---------------------------<br> <br> Ask an Algorithm: Using Machine Learning to study Human Speech <br> Will Styler (University of Michigan)<br> <br> 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. <br> <br> 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. <br> <br> 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. <br> <br> 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.<br> <br> </div> <p><br> </p> </div> </div> _______________________________________________<br> lin-grad mailing list<br> <a href="mailto:lin-grad@lin.msu.edu" target="_blank">lin-grad@lin.msu.edu</a><br> <a href="http://mailman.egr.msu.edu/mailman/listinfo/lin-grad" rel="noreferrer" target="_blank">http://mailman.egr.msu.edu/mailman/listinfo/lin-grad</a><br> </div></div><div dir="ltr">-- <br></div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr">Suzanne Evans Wagner<div>Associate Professor of Linguistics</div><div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small">B-401 Wells Hall<br>Department of Linguistics and Languages<br>Michigan State University<br>East Lansing, MI 48824<br><br>Tel: +1 (517) 355-9739<br><a href="http://www.msu.edu/~wagnersu" target="_blank" style="color:rgb(17,85,204)">http://www.msu.edu/~wagnersu</a><br><a href="http://sociolinguistics.linglang.msu.edu/" target="_blank" style="color:rgb(17,85,204)">sociolinguistics.linglang.msu.edu</a></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small"><br></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small">Office hours:<span class="inbox-inbox-inbox-Apple-converted-space"> </span><a href="http://swagner.youcanbook.me/" target="_blank" style="color:rgb(17,85,204)">http://swagner.youcanbook.me</a></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small"><br></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small"><span style="font-size:12.8px">Associate editor, <a href="http://www.degruyter.com/view/j/lingvan" target="_blank" style="color:rgb(17,85,204);font-style:italic">Linguistics Vanguard</a></span><br></div><div style="color:rgb(34,34,34);font-family:arial,sans-serif;font-size:small">Co-editor,<span class="inbox-inbox-inbox-Apple-converted-space"> </span><i><a href="http://www.routledge.com/books/series/RSLC/" target="_blank" style="color:rgb(17,85,204)">Routledge Studies in Language Change</a></i></div></div><div><br></div></div></div>