EduSpeak®
The EduSpeak SDK is a speech recognition system for computer learning and training applications such as foreign language education, English as a second language (ESL), reading development and interactive tutoring, and corporate training and simulation. Access to its high-accuracy continuous speaker-independent speech recognition engine, is supported through several programming interfaces, such as Macromedia Director and Microsoft ActiveX, making it easy for developers of interactive, multimedia learning products to integrate voice input in their products. For developers of computer-aided language learning and ESL products, SRI's patented pronunciation scoring technology provides feedback to language learners to help them compare how their spoken word or phrase pronunciation compares with that of a native speaker of the language they are learning.
- Wide range of programming interfaces (Director, ActiveX, C, Java) - Faster integration into multimedia software
- Works for child and adult voices - Unparalleled accuracy for children ages 4 and up
- Works for native and non-native speakers - Robust to strong accents
- Speaker independent - No tedious user training session required
- Scores pronunciation like a human - Feedback for language learners by word, phrase, or passage
- Dynamically loadable vocabulary and grammars - Lesson design flexibility
Software Development Kit:
Recognition Engine: C/C++ DLL
Software wrappers: Macromedia Director and Flash, ActiveX, Java
Development environments: C/C++, Microsoft Visual Basic and .NET, Macromedia Director and Flash, HTML/JavaScript
Languages Supported (Native and non-native):
Adults: American English, Latin American Spanish, French, German, Chinese (Mandarin), Arabic (Egyptian), UK English, Australian/NZ English, Japanese, Swedish, Tagalog (Filipino)
Children: American English (Ages 4 to 15)
Download Size (Compressed):
EduSpeak recognition engine: 0.6MB
Acoustic model: 2.0MB
End User System Requirements
Operating System: Windows 98/2000/NT/XP
CPU: Pentium 512MHz or higher
System RAM: 128MB or higher
Other: Noise-canceling headset microphone preferred
Application Memory Requirements
Fixed grammar type of application: ~10MB RAM (varies with application)
Dynamically-loaded type of application ~20MB RAM (varies with application)