Emotion-aware voice assistant
AssigneeCerence Operating Company
InventorsRaymond Brueckner, Markus Funk
Life of this patent
Estimating the term…
Abstract
An interface customized to a detected emotional state of a user is provided. Audio signals are received from at least one microphone, the audio signals being indicative of spoken words, phrases, or commands. A wake-up word (WuW) is detected in the audio signals. An emotion is also detected in the audio signals containing the WuW. An emotion-aware processing system is configured according to the detected emotion. A voice control session is performed using the emotion-aware processing system configured according to the detected emotion.
Claims25
A system for providing an interface customized to a detected emotional state of a user, comprising:
- at least one microphone configured to produce audio signals indicative of spoken words, phrases, or commands;
- and
- a processor programmed to:
- receive the audio signals from the at least one microphone,
- detect a wake-up word (WuW) in the audio signals,
- detect, in parallel to the detection of the WuW, an emotion in the audio signals detected as containing the WuW using an emotion detector, the emotion detector being trained to detect emotional state in the audio signals on a corpus of audio signals containing the WuW alone,
- responsive to detection of the WuW and the emotion, configure an emotion-aware processing system according to the detected emotion, and
- perform a voice control session triggered by the detected WuW, using the emotion-aware processing system configured according to the detected emotion to recognize and respond to additional spoken input.
A method for providing an interface customized to a detected emotional state of a user, comprising:
- receiving audio signals from at least one microphone, the audio signals being indicative of spoken words, phrases, or commands;
- detecting a wake-up word (WuW) in the audio signals;
- detecting, in parallel to the detection of the WuW, an emotion in the audio signals detected as containing the WuW using an emotion detector, the emotion detector being trained to detect emotional state on a corpus of audio signals containing the WuW alone;
- responsive to detection of the WuW and the emotion, configuring an emotion-aware processing system according to the detected emotion;
- and
- performing a voice control session triggered by the detected WuW, using the emotion-aware processing system configured according to the detected emotion to recognize and respond to additional spoken input.
Dependencies are inferred from the claim text.