{"id":869,"date":"2019-03-25T14:24:24","date_gmt":"2019-03-25T14:24:24","guid":{"rendered":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/?p=869"},"modified":"2019-03-26T11:47:21","modified_gmt":"2019-03-26T11:47:21","slug":"automatic-transcription-software-2-6-synote","status":"publish","type":"post","link":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/posts\/869","title":{"rendered":"Automatic Transcription Software (2\/6) \u2013 Synote"},"content":{"rendered":"<p>This is the second post of this series about the project\u00a0<a href=\"https:\/\/blog.ucem.ac.uk\/onlineeducation\/posts\/433\">Evaluation of Transcription Software<\/a>\u00a0 looking at Synote.\u00a0 You can read the previous blog in this series from\u00a0\u00a0<a href=\"https:\/\/blog.ucem.ac.uk\/onlineeducation\/posts\/591\">Automatic Transcription Software (1\/6) \u2013 Zoom<\/a>.<\/p>\n<p>I tried automatic transcription with eight voice recordings from a purposely selected sample of UCEM employees reading a script of 1000 words containing\u00a0\u00a0paragraphs relating to various subject disciplines in the built environment.<\/p>\n<p>Synote is a transcription software that can be used collaboratively. So, if all students have accounts they are able to make corrections in the transcripts should there be any errors. However, at UCEM we used Synote in a\u00a0 slightly different\u00a0 way where we did not provide all students with accounts. In this model,\u00a0 the collaborative corrections of transcripts that happen in the way Synote is built to be used is taken away hence there has to be an intermediary , an admin, between students and Synote to\u00a0 correct any reported errors.<\/p>\n<p>As I have already mentioned in my previous blog post I used\u00a0Word Error Rate (WER),\u00a0 as a measure of accuracy:<\/p>\n<p><strong>WER = (Substitution + Deletion + Insertions) \/ N<\/strong><\/p>\n<p>where N is the total number of words in the reference transcript (Apone, Botkin, Brooks, &amp; Goldberg, 2011).<\/p>\n<p>However, WER is not a great way to check accuracy as it considers all words as equal.\u00a0 Here I have calculated the WER and one minus WER as a percentage taken as the accuracy rate.<\/p>\n<p>Synote worked really well for some users but not so for others.<\/p>\n<p>The highest accuracy rate was recorded for a native British\u00a0 speaker&#8217;s recording. However, for non-native speakers the accuracy rate was much lower than what we hoped for.\u00a0 With just above 30% accuracy rate for some transcripts this was not going to be accurate enough as an accessibility aid.<\/p>\n<figure id=\"attachment_872\" aria-describedby=\"caption-attachment-872\" style=\"width: 602px\" class=\"wp-caption alignnone\"><a href=\"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote.png\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-872 \" src=\"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote-1024x709.png\" alt=\"Synote Transcription Accuracy Rate shown in a graph it varies from about 86% to just above 30%\" width=\"602\" height=\"417\" srcset=\"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote-1024x709.png 1024w, https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote-300x208.png 300w, https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote-768x532.png 768w, https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-content\/uploads\/2019\/03\/Blog-Synote.png 1073w\" sizes=\"(max-width: 602px) 100vw, 602px\" \/><\/a><figcaption id=\"caption-attachment-872\" class=\"wp-caption-text\">Synote Transcription Accuracy Rate<\/figcaption><\/figure>\n<p>I will blog about the other automatic transcription software in due cause.<\/p>\n<h2>Reference<\/h2>\n<p>Apone, T., Botkin, B., Brooks, M., &amp; Goldberg, L. (2011). Caption Accuracy Metrics Project: Research into Automated Error Ranking of Real-time Captions in Live Television News Programs. Retrieved from http:\/\/ncam.wgbh.org\/file_download\/136<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This is the second post of this series about the project\u00a0Evaluation of Transcription Software\u00a0 looking at Synote.\u00a0 You can read the previous blog in this&hellip;<\/p>\n","protected":false},"author":10,"featured_media":843,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[36,30,1],"tags":[26,93,94],"_links":{"self":[{"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/posts\/869"}],"collection":[{"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/comments?post=869"}],"version-history":[{"count":3,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/posts\/869\/revisions"}],"predecessor-version":[{"id":873,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/posts\/869\/revisions\/873"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/media\/843"}],"wp:attachment":[{"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/media?parent=869"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/categories?post=869"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.ucem.ac.uk\/onlineeducation\/wp-json\/wp\/v2\/tags?post=869"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}