InToneTM technology
A microscopic lense into human emotions
InTone™ is powered by Nemesysco’s LVA™ (Layered Voice Analysis) core – a technology that has been meticulously perfected for over two decades. At the heart of LVA™ are proprietary sets of vocal parameters found through extensive research to correlate with many different key human emotions. These vocal parameters were classified from a large repository of human voice recordings captured in different languages and numerous life situations – from call centers through police interrogations to controlled experiments. Many of the parameters that LVA™ extracts are new to the world of phonetics. Focusing on uncontrolled properties of the human voice, LVA™ is highly-sensitive to the actual feelings and emotional reactions of the speaker at a level that cannot be controlled by the speaker or easily noticed by the listener.
While InTone™ is a powerful ready-made solution for call centers with existing infrastructure, Nemesysco's core technology is also available for integration into your own solutions via SDK/API. We provide different development kits for system developers wanting to implement emotion detection into their platforms. For information, Please visit Nemesysco's QA7 website here.
InTone features the built-in ability to detect and measure a wide range of emotions and cognitive states. These emotion sets include “Stress”, “Anger”/ “Aggression”, “Happiness”, “Unease”, “Energy level” and many more. Combining these built-in capabilities with BI/AI engines, it enables users to define, train and detect additional emotional states to meet mission-specific needs. This unique combination of out-of-the-box emotion detection, together with the ability to train the system to detect other emotional areas of interest – in real-time or from pre-recorded sources, makes InTone the most versatile voice analysis technology available today.
