Speech Recognition

HOME >
Speech Recognition >
Selvy STT-Edu

Selvy STT-Edu

Selvy STT-Edu is a multilingual education assistant solution (English, Chinese, Japanese and Korean), which uses speech recognition technology.
It supports a variety of servers, PCs and operating systems including embedded Android, iOS, WinCE, etc. It is particularly effective for improving English listening and speaking skills, and provides evaluation results and a report on English pronunciation.
In the field of education (including language institutes and education providers), Selvy STT-Edu provides a language learner with the word position and pronunciation information, as well as feedback on the pronunciation when compared to that of a native speaker and TTS.

Major Application Examples

Language institutes and websites
for language-related content devices
Provides English, Chinese and Japanese language institutes curriculum providers with speech recognition technology, enabling evaluative learning and pronunciation accuracy feedback Educational device providers

Provides an educational speech recognition engine optimized for various operating systems

Features and benefits of the solution

Learning to speak English
using speech recognition

Through self-directed learning,
by listening and repeating
the words and sentences,
users can improve
their English pronunciation.

Improving English pronunciation

Analyzes the user's pronunciation to
provide word- and phoneme-specific reports.

Allows users to check their pronunciation
by listening to their own recorded data.

Listening to a native speaker's pronunciation

A user can open an English TTS sound source
as well as a file recorded by a native speaker
in order to listen and repeat.

Convenience of being able to
add and modify contents

A user may add or modify the contents to study
only the required or desired words or sentences

Storing the user settings and history

The "History" feature lets users pick up
where they left off and continue learning.

Improving speaking skills
using RolePlay

By using the English TTS and STT features,
a user can learn how to speak English alone.

RolePlay allows a user to switch roles freely
with the computer when practicing.

Learning to speak English using speech recognition Through self-directed learning, by listening and repeating the words and sentences, users can improve their English pronunciation.	Improving English pronunciation Analyzes the user's pronunciation to provide word- and phoneme-specific reports. Allows users to check their pronunciation by listening to their own recorded data.	Listening to a native speaker's pronunciation A user can open an English TTS sound source as well as a file recorded by a native speaker in order to listen and repeat.
Convenience of being able to add and modify contents A user may add or modify the contents to study only the required or desired words or sentences	Storing the user settings and history The "History" feature lets users pick up where they left off and continue learning.	Improving speaking skills using RolePlay By using the English TTS and STT features, a user can learn how to speak English alone. RolePlay allows a user to switch roles freely with the computer when practicing.