EduSpeak® speech recognition toolkit

Increasingly, educators, publishers, employers, and consumers use interactive, computer-based materials to teach or train students of all ages. Adding speech recognition is a principal way to enhance these materials’ interactivity and ultimate effectiveness. However, general-purpose speech recognition systems lack the broad array of multimedia development interfaces essential for use with diverse educational platforms.

Unlike those general-purpose systems, EduSpeak works with Flash, Java, ActiveX, and C/C++. EduSpeak works for both adult and child voices. EduSpeak excels at recognizing both native and non-native speakers. And no other speech recognition system includes SRI’s patented human-calibrated pronunciation-scoring technology—a critical product differentiator for interactive language learning and assessment, and for reading instruction applications. EduSpeak is a product of SRI’s Speech Technology and Research Laboratory, a world leader in speech technology research and development.

Key features

• Wide range of programming interfaces
• Recognizes adult and child voices
• Works for native and non-native speakers
• Human-calibrated pronunciation scoring
• Deployable locally, via download, CD- or DVD-ROM media, or client/server or cloud services

Specifications

Operating systems

• Windows XP or later
• Mac OS X 10.4 or later
• Linux
• Android

Development environments

• Flash, Java (via JNI), ActiveX, C/C++, Java Script, and Director
• Client/server versions available
• All major web browsers

Supported languages

• Adults: American and British English, Latin American Spanish, Iraqi Arabic, Pashto, and Dari (others on request)
• Children: American English
• Grammars: GSL/JSGF forms; static or dynamic; natural language understanding

Learn more about our innovations at school and in the workplace.