18297509. CONTEXT-AWARE FALSE TRIGGER MITIGATION FOR AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS OR OTHER SYSTEMS simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
CONTEXT-AWARE FALSE TRIGGER MITIGATION FOR AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS OR OTHER SYSTEMS
Organization Name
Inventor(s)
Cindy Sushen Tseng of Santa Clara CA (US)
Srinivasa Rao Ponakala of Sunnyvale CA (US)
Myungjong Kim of Milpitas CA (US)
Taeyeon Ki of Milpitas CA (US)
Vijendra Raj Apsingekar of San Jose CA (US)
CONTEXT-AWARE FALSE TRIGGER MITIGATION FOR AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS OR OTHER SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18297509 titled 'CONTEXT-AWARE FALSE TRIGGER MITIGATION FOR AUTOMATIC SPEECH RECOGNITION (ASR) SYSTEMS OR OTHER SYSTEMS
Simplified Explanation
The method described in the patent application involves using an audio input and location data from an electronic device to determine the likelihood of a false trigger for automatic speech recognition.
- Obtaining an audio input and a location associated with an electronic device
- Generating an audio embedding associated with the audio input
- Determining the difference between the audio embedding of the input and a known user
- Determining the difference between the location of the device and a known location of the user
- Using a false trigger mitigation system to calculate the probability of a false trigger for automatic speech recognition
- Deciding whether to perform automatic speech recognition based on the calculated probability
---
- Potential Applications
- Automatic speech recognition systems
- Security systems for electronic devices
- Location-based authentication systems
- Problems Solved
- Minimizing false triggers for automatic speech recognition
- Enhancing security by verifying user identity based on audio input and location data
- Benefits
- Improved accuracy of automatic speech recognition
- Enhanced security measures for electronic devices
- Customized user experience based on location and audio input
Original Abstract Submitted
A method includes obtaining an audio input and a location associated with an electronic device. The method also includes generating an audio embedding associated with the audio input. The method further includes determining a first difference between the audio embedding associated with the audio input and an audio embedding associated with a known user. The method also includes determining a second difference between the location associated with the electronic device and a known location associated with the known user. The method further includes generating, using a false trigger mitigation (FTM) system, a probability of the audio input including a false trigger for automatic speech recognition based on the audio input, the first difference, and the second difference. In addition, the method includes determining whether to perform automatic speech recognition based on the probability.
