Spoken-Language-Proficiency-Asssessment-BASIC-VER0
The first step to create an Automatic Spoken Language Assessment system (Prosody focus) The code reads speech data from an audio file and measures prosody, pronunciation and structure. It was architected and assembled in PRAAT. It created a real-time and comprehensive performance report. The analytical module o the code is pure mathematics and statistics FOR the BASIC VERO
Branch 1
License: APA 2.02 UKREF
Acknowledge The scientific way to measure one’s Reading/Speaking rate is in syllables per second.
The Reading OSP’s estimate of the “Reading Rate” is obtained by timing the user while reading a selection of text with a known syllables count.
The Reading OSP evaluates the competency of the user by employing mathematical formulas and ETS’s independent speaking rubrics and philosophy (Educational Testing Service-USA).
The Reading OSP 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.