{"id":51562,"date":"2020-01-08T11:00:17","date_gmt":"2020-01-08T08:00:17","guid":{"rendered":"https:\/\/www.englishcentral.com\/blog\/?p=51562"},"modified":"2024-05-13T10:06:04","modified_gmt":"2024-05-13T07:06:04","slug":"englishcentral-intellispeech-technology","status":"publish","type":"post","link":"https:\/\/www.englishcentral.com\/blog\/en\/news\/englishcentral-intellispeech-technology\/","title":{"rendered":"EnglishCentral IntelliSpeech\u2120 Technology"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t

EnglishCentral IntelliSpeech\u2120 Technology<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n
\n\t
\n\t\t
\n\t\t\t

EnglishCentral\u2019s \u201cspecial sauce\u201d has always been our internally developed IntelliSpeech\u2120 assessment technology. Teachers appreciate how IntelliSpeech\u2120 motivates students to speak outside of the classroom. Students appreciate the instant feedback and the game dynamic of trying to improve their speaking scores.<\/p>\n

EnglishCentral\u2019s IntelliSpeech\u2120 is trained on hundreds of millions of lines of speech from students from over 100 countries, using the latest Machine Learning techniques. It assesses learners\u2019 speaking ability across the following dimensions:<\/p>\n\n\t\t<\/div>\n\t<\/div>\n<\/div><\/div><\/div>

\n\t
\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n<\/div><\/div><\/div><\/div>\n\t
\n\t\t
\n\t\t\t

Pronunciation<\/strong> measures the acoustical qualities of students\u2019 speech over 64,000 possible triphones (combinations of phonemes), stress and prosodics.<\/p>\n

Fluency<\/strong> is still based on duration and pause rate of the speech.<\/p>\n

Completion<\/strong> is still based on whether the user speaks all words, or drops words.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t
\n\t\t\t

Error Types<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

As the learner speaks, Intellispeech\u2120 provides feedback according to the following types of errors:<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t\n\t\t
\n\t\t\t
<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Line Score<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Learners get a line score between 0 and 100 points for each line spoken. Learners lose points for each error made. The amount of points learners lose per error is weighted based on the number of words in the line. For shorter lines, learners lose more points per error than for longer lines.<\/p>\n

Only the final version of each line spoken counts towards the users final score on the Video Grade. So, if a line is repeated several times, only the last version counts towards the Video Grade.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t
\n\t\t\t

Video Grades<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

The video grade is the cumulative measure (i.e. the weighted average) of the line scores received by the learner from speaking lines in the video.<\/p>\n

Intellispeech\u2120 computes a percentile relative to other learners to produce a video grade. For instance, if we determine that the speech for the video was 75% better than other learners, the learner would get a \u201cB+\u201d as a video grade.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Percentiles are mapped to grades as follows:<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Pronunciation Center<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

The Pronunciation Center (\u201cPron Center\u201d) on EnglishCental is where students\u2019 feedback and progress on their pronunciation is tracked and where they can find exercises to help remediate their pronunciation challenges.<\/p>\n

At the heart of the Pron Center are the 4 steps of our Pronunciation Learning Cycle:<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Pronunciation Courses<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

IntelliSpeech\u2120 has analyzed our users English pronunciation over hundreds of millions of recorded utterances and identified the most common problematic sounds of speakers for each native language region. Based on this analysis and speech data, we have designed pronunciation courses \u2014 Top 10 Challenges \u2014 where learners can focus on the most challenging Sounds for speakers from their native language, using authentic videos. We currently have customized pronunciation courses for: Japanese, Korean, Spanish, Portuguese, Turkish, French, Vietnamese, and Arabic.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Our Speech Database<\/h2>\n\n\t\t<\/div>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

For the last 10 years, our learners have provided us a trove of data (over 600,000,000 speech utterances from over 100 countries) on how they learn English.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n\n\t

\n\t\t\n\t\t
\n\t\t\t
\"\"<\/div>\n\t\t<\/figure>\n\t<\/div>\n\n\t
\n\t\t
\n\t\t\t

Our reference models are also training on large amounts of data collected from native speakers speaking the authentic speech from our videos (as opposed to many other corpora which may contain artificial \u201cread speech\u201d).<\/p>\n

We use this data to create a \u201cMachine Learning Loop\u201d that combines this large data set with feedback from a team of over 600 trained professional English teachers who have analyzed student speaking ability in over 500,000 1-on-1 live sessions. The result is the \u201cmachine\u201d (our online self-study platform) learns from the feedback teachers provide, and at the same time, teachers learn from the feedback the machine provides on learners\u2019 strengths and weaknesses.<\/p>\n\n\t\t<\/div>\n\t<\/div>\n<\/div><\/div><\/div><\/div>\n<\/div>","yb_wpb_post_custom_css":""},"excerpt":{"rendered":"

EnglishCentral\u2019s IntelliSpeech\u2120 is trained on hundreds of millions of lines of speech from students from over 100 countries, using the latest Machine Learning techniques.<\/p>\n","protected":false},"author":5,"featured_media":55463,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[734],"tags":[],"class_list":["post-51562","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","generate-columns","tablet-grid-50","mobile-grid-100","grid-parent","grid-33"],"image_url":"https:\/\/www.englishcentral.com\/blog\/wp-content\/uploads\/2020\/01\/englishcentral_intellispeech_technology.webp","author_name":"Irem Ugurlu","_links":{"self":[{"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/posts\/51562","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/comments?post=51562"}],"version-history":[{"count":11,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/posts\/51562\/revisions"}],"predecessor-version":[{"id":52922,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/posts\/51562\/revisions\/52922"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/media\/55463"}],"wp:attachment":[{"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/media?parent=51562"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/categories?post=51562"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.englishcentral.com\/blog\/wp-json\/wp\/v2\/tags?post=51562"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}