Speech technology and research lab
Communicating with, and through, computer applications
The Speech Technology and Research (STAR) Laboratory brings together a multidisciplinary mix of engineers, computer scientists and linguists. Together, our experts build systems for a wide range of applications including signal processing; data indexing and mining; and computer-aided learning. SRI’s speech and language technologies allow us to interact more naturally with computing applications and provide a wealth of actionable information about our intentions, health, and emotional state.
Core technologies and applications
Real-world impact
-
Case study: A game-changing multimedia processing platform for national defense and commercial innovation
“One of the compelling things about working on speech technology today is that, for all the incredible capabilities that have emerged in the past decade, we know there’s so much more we can do. As AI and machine learning continue to become more precise and efficient, the OLIVE platform will only grow more powerful and…
-
What’s next in AI-based translation?
Reviewing the Apple AirPods Pro 3, The New York Times turned to SRI’s Dimitra Vergyri to unpack the significance of recent advances in translation tech.
-
SRI’s AI-driven voice analysis could help screen for mental health conditions
Researchers at SRI are developing tools to help clinicians keep a close eye on depression, PTSD, and other mental health issues.
Featured researchers
-
Dimitra Vergyri
Director, Speech Technology and Research Laboratory (STAR)
-
Horacio Franco
Chief Scientist, Speech Technology and Research Laboratory
-
Aaron Lawson
Assistant Laboratory Director, Speech Technology and Research Laboratory
-
Martin Graciarena
Technical Manager, Speech Technology and Research Laboratory
-
Mitchell McLaren
Senior Computer Scientist, Speech Technology and Research Laboratory
-
Harry Bratt
Senior Computer Scientist, Speech Technology and Research Laboratory
Platforms
Publications
-
Toward Fail-Safe Speaker Recognition: Trial-Based Calibration with a Reject Option
In this work, we extend the TBC method, proposing a new similarity metric for selecting training data that results in significant gains over the one proposed in the original work.
-
Resilient Data Augmentation Approaches to Multimodal Verification in the News Domain
Building on multimodal embedding techniques, we show that data augmentation via two distinct approaches improves results: entity linking and cross-domain local similarity scaling.
-
Natural Language Access: When Reasoning Makes Sense
We argue that to use natural language effectively, we must have both a deep understanding of the subject domain and a general-purpose reasoning capability.