Qualcomm incorporated (20240105206). SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS simplified abstract
Contents
- 1 SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS
Organization Name
Inventor(s)
Hesu Huang of San Diego CA (US)
Leonid Sheynblat of Hillsborough CA (US)
Vinesh Sukumar of Fremont CA (US)
Ziad Asghar of San Diego CA (US)
Joel Linsky of San Diego CA (US)
Justin Mcgloin of Los Altos CA (US)
Tong Tang of Escondido CA (US)
SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240105206 titled 'SEAMLESS CUSTOMIZATION OF MACHINE LEARNING MODELS
Simplified Explanation
The present disclosure describes a method for improving machine learning through voice data analysis and user verification.
- Voice data from a first user is received.
- If the voice data includes a defined keyword, a user verification score is generated using a machine learning model.
- The quality of the voice data is determined.
- If the user verification score and quality meet certain criteria, a second user verification model is updated based on the voice data.
Potential Applications
This technology could be applied in various industries such as security, customer service, and personal assistant applications.
Problems Solved
This technology helps in enhancing user verification processes and improving the accuracy of machine learning models.
Benefits
The benefits of this technology include increased security, improved user experience, and enhanced machine learning capabilities.
Potential Commercial Applications
Potential commercial applications of this technology include voice recognition systems, fraud detection tools, and personalized recommendation engines.
Possible Prior Art
Prior art in this field may include existing voice recognition systems, user verification methods, and machine learning models used for similar purposes.
Unanswered Questions
1. How does this technology handle different accents and languages in voice data analysis? 2. What measures are in place to ensure the privacy and security of the voice data collected for user verification purposes?
Original Abstract Submitted
certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. voice data from a first user is received. in response to determining that the voice data includes an utterance of a defined keyword, a user verification score is generated by processing the voice data using a first user verification machine learning (ml) model, and a quality of the voice data is determined. in response to determining that the user verification score and determined quality satisfy one or more defined criteria, a second user verification ml model is updated based on the voice data.