Welcome to Sab-AI lab
A boutique AI lab in Nagoya-Japan.
This is a brief of the Reading-Rater technical narrative developed for UP INC-OSAKA Japan.
The narrative sets about the technology's scope of works, accuracy, the-best-use and wayforwards.
A boutique AI lab in Nagoya-Japan.
This is a brief of the Reading-Rater technical narrative developed for UP INC-OSAKA Japan.
The narrative sets about the technology's scope of works, accuracy, the-best-use and wayforwards.
This version of Rater is customized for UP, an English School in Osaka-Japan. This version can measure the “Reading Rate” of a user (reader) and compare it with the average rate of non-native and native speakers.
Total reading fluency refers to the ability of readers to read the words in text effortlessly and efficiently (automaticity) with meaningful expression that enhances the meaning of the text (prosody). Fluency takes phonics or word recognition to the next level. While many readers can decode words accurately, they may not be fluent or automatic in their word recognition. These readers tend to expend too much of their limited mental energy on figuring out the pronunciation and meaning of words, energy that is taken away from that more important task in reading comprehension — getting to the text’s overall meaning. Thus, the lack of fluency often results in poor comprehension.
Fluent readers, on the other hand, are able to read words accurately and effortlessly. They recognize words and phrases instantly on sight. A minimal amount of cognitive energy is expended in decoding the words. This means, then, that the maximum amount of a reader’s cognitive energy can be directed to the all-important task of making sense of the text.
The second component to fluency is prosody , or reading with expression. A key characteristic of fluent oral reading (or speech, for that matter) is the ability to embed appropriate expression into the reading.Fluent readers raise and lower the volume and pitch of their voices, they speed up and slow down at appropriate places in the text, they read words in meaningful groups or phrases, they pause at appropriate places within the text. All these are elements of expression, or what linguists have termed prosody. Prosody is essentially the melody of language as it is read or spoken. By embedding prosody in our oral language (read or spoken), we are adding meaning to the text.
The scientific way to measure one’s Reading/Speaking rate is in syllables per second.
Rater’s estimate of the “Reading Rate” is obtained by timing the user while reading a selection of text with a known syllables count.
Rater evaluates the competency of the user by employing mathematical formulas and ETS’s independent speaking rubrics and philosophy (Educational Testing Service-USA).
Rater went through a Machine learning session, with an audio dataset of non-native and native English speakers. These audios ranged from just 2 minutes in length to just under 5 minutes. Speakers' topics vary widely, total 9036 minutes audios.
For each session of the student training, we recommend teachers select five types of sentences: wh- questions, declarative sentences, yes-no questions, tag questions, closed-choice alternative questions
which can help eliminate or counterbalance the effects of different sentence types on suprasegmental features produced by learners and reveal the segmental features in different sentence types.
Suggested pausing
Suggested intonation
Suggested linking
Suggested lexical stress for multisyllabic words
| Dataset | Metric | Accuracy | Precision | Recall (Sensitivity) |
|---|---|---|---|---|
| For native | Reading Rate | 70% | 83% | 68% |
| For Japanese-English speaker | Reading Rate | 84% | 88% | 95% |
sabailabo@gmail.com
Sab-AI Lab 愛知県 名古屋市 昭和区 広路町字梅園 １０-４