Sensing what people say, and how they say it.
SenSay Analytics is platform that performs real-time speaker state classification from spoken audio. SRI is working with research and industry partners using SenSay Analytics to estimate speaker state such as emotion, sentiment, cognition, health, mental health and communication quality in a range of end applications including:
- Personal assistants
- Health monitoring
- Service robots
- Interpersonal skills
- Driver monitoring
- Gaming
- Education
- Marketing/advertising
How it works
At sub-second intervals, the SenSay platform updates both features and class estimates using advanced signal features that capture spectral, prosodic, articulatory, auditory, discourse and fluency characteristics, as well as features designed specifically for robustness to noise and reverberation.
SenSay can analyze the features from the signal alone or combined with automatic speech recognition to model word-based information via sentiment models. Features are modeled using state-of-the-art machine learning approaches appropriate to the task, training data and application constraints.
SenSay advantages
Speed
Platform provides class and feature updates at < 1 second; crucial for applications such as driver monitoring, dialog system response and customer service.
Control, privacy
SenSay can run in cloud, on laptop/desktop or in client-hosted environment.
Configurability
Deploy on premises or in the cloud. Use as a feature extractor, class predictor or both. Use with or without automatic speech recognition.
Extensibility
APIs let clients add additional sensor capabilities such as video-based or physiological features.
Customizability
Platform can be adapted to task, domain, language, single- or multi-party conversations.
Scalability
SenSay is architected to support simultaneous live streams.
Contact
For more information or to work with us, e-mail sensay-info@speech.sri.com.