{"id":50400,"date":"2021-02-26T17:04:55","date_gmt":"2021-02-26T22:04:55","guid":{"rendered":"https:\/\/languagelog.ldc.upenn.edu\/nll\/?p=50400"},"modified":"2021-02-26T17:19:10","modified_gmt":"2021-02-26T22:19:10","slug":"articulate-tory-gestures","status":"publish","type":"post","link":"https:\/\/languagelog.ldc.upenn.edu\/nll\/?p=50400","title":{"rendered":"Articulate Tory gestures"},"content":{"rendered":"<p>At our most recent Penn Phonetic Lab meeting, we heard a (virtual) talk by <a href=\"https:\/\/pages.ucsd.edu\/~mgarellek\/\" target=\"_blank\" rel=\"noopener\">Marc Garellek<\/a> on the topic \"Reconsidering voicing during glottal sounds\". The talk was quite interesting, but more relevant for a general audience was what happened when someone turned on Zoom's \"Live Transcription\" feature:<br \/>\n<a href=\"http:\/\/languagelog.ldc.upenn.edu\/myl\/ZoomLiveTranscription.png\"><img decoding=\"async\" title=\"Click to embiggen\" src=\"http:\/\/languagelog.ldc.upenn.edu\/myl\/ZoomLiveTranscription.png\" width=\"490\" \/><\/a><br \/>\n<!--more--><\/p>\n<p>Overall the accuracy was not terrible, as such things go these days &#8212; I'm not able to give an accurate Word Error Rate number, since I don't think the presentation was recorded, but I'd estimate it at about 25%. The fun part was what the errors were.<\/p>\n<p>For example, the phrase \"articulate Tory\" occurred four times during the 60 seconds or so of transcript I saved, and these were not references to <a href=\"https:\/\/en.wikipedia.org\/wiki\/Yorick_Wilks\" target=\"_blank\" rel=\"noopener\">Yorick Wilks<\/a>.<\/p>\n<p>Rather,\u00a0 Marc's subject naturally involved the word <em>articulatory<\/em>, and each time he used that word, Zoom transcribed it as \"articulate Tory\". And whenever he said <em>glottalization<\/em> it was transcribed as \"globalization\". So when he said (what I believe was)<\/p>\n<p style=\"padding-left: 40px;\"><span style=\"color: #000080;\">For many languages, we really need to only assume two articulatory gestures here, aspiration and glottalization.<\/span><\/p>\n<p>&#8230; Zoom transcribed:<\/p>\n<p style=\"padding-left: 40px;\"><span style=\"color: #800000;\">For many languages, we really need to only assume to articulate Tory gestures here, aspiration, and globalization<\/span><\/p>\n<p>I suspect that Yorick is more committed to aspirational gestures than to globalization-related ones, but I'll leave it to him to let us know.<\/p>\n<p>Among other fun errors, <em>creaky vowel<\/em> was regularly rendered as \"creek evil\",\u00a0 and <em>glottal<\/em> was sometimes rendered as \"rebuttal\" (so <em>Do different glottal sounds differ in their voicing<\/em> -&gt; \"Do different rebuttal sounds differ in their voicing\"), and <em>h<\/em> as \"page\" or \"stage\" (so <em>hook top h<\/em> -&gt; \"hook top page\" and <em>voiced h<\/em> as \"voice stage\"), and so on.<\/p>\n<p>So the subtitles\/transcripts are probably helpful for some non-native speakers and perhaps those with weak network connections, but &#8230;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>At our most recent Penn Phonetic Lab meeting, we heard a (virtual) talk by Marc Garellek on the topic \"Reconsidering voicing during glottal sounds\". The talk was quite interesting, but more relevant for a general audience was what happened when someone turned on Zoom's \"Live Transcription\" feature:<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[299],"tags":[],"class_list":["post-50400","post","type-post","status-publish","format-standard","hentry","category-elephant-semifics"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/posts\/50400","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=50400"}],"version-history":[{"count":8,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/posts\/50400\/revisions"}],"predecessor-version":[{"id":50408,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=\/wp\/v2\/posts\/50400\/revisions\/50408"}],"wp:attachment":[{"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=50400"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=50400"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/languagelog.ldc.upenn.edu\/nll\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=50400"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}