Speech, Language, and Audio | SRI International
This is an archived website. Go to the current SRI website

Toggle Menu

Speech, Language, and Audio

From soothing a crying baby to rallying millions to a cause, the human voice is a powerful tool. Speech and language allow us to interact naturally with a variety of computing applications, as well as providing a wealth of information about our relationships, intentions, health, and emotional state.

For government and commercial clients, SRI's Speech Technology and Research (STAR) Laboratory creates software for signal processing, phonetics, mathematical modeling, acoustics, data indexing and mining, language translation, and computer-aided learning. For tailored client solutions, SRI offers advanced product prototyping and customization and turnkey product development.

SRI also develops speech and audio technology for use in challenging audio environments, where it can be extremely difficult to understand the speech, identify the speaker or language, or even just detect whether speech is present. SRI has honed speaker identification and verification techniques for biometric applications.

Developers incorporate SRI’s DynaSpeak® and EduSpeak® technologies, packaged as software development kits, into their products and services.

Market leader Nuance, now a billion-plus-dollar company, was spun off from SRI in the 1990s to exploit STAR Laboratory technology. Today, developers incorporate SRI speech technologies, packaged as software development kits, into their products and services.


Open Language Interface for Voice Exploitation (OLIVE)

Open Language Interface for Voice Exploitation (OLIVE)

Spotting Audio-Visual Inconsistencies (SAVI)

SRI is finding new ways to detect altered and tampered video.

three young students working on a laptop together

Speech-Based Learning Analytics for Collaboration

SRI is investigating whether and how students’ speech can be used to determine how well they collaborate during interactive learning activities.


Robust Automatic Transcription of Speech–Transition (RATS-T)

SRI is improving the robustness of speech processing technologies and transitioning them to government partners for use in highly noisy operational audio conditions.