GOOGLE LLC (20240296848). AUTOMATIC GENERATION AND/OR USE OF TEXT-DEPENDENT SPEAKER VERIFICATION FEATURES simplified abstract
Contents
AUTOMATIC GENERATION AND/OR USE OF TEXT-DEPENDENT SPEAKER VERIFICATION FEATURES
Organization Name
Inventor(s)
Matthew Sharifi of Kilchberg (CH)
AUTOMATIC GENERATION AND/OR USE OF TEXT-DEPENDENT SPEAKER VERIFICATION FEATURES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240296848 titled 'AUTOMATIC GENERATION AND/OR USE OF TEXT-DEPENDENT SPEAKER VERIFICATION FEATURES
The patent application relates to the automatic generation of speaker features for text-dependent speaker verifications (TD-SVs) for a user, using audio data captured during interactions with an automated assistant.
- Speaker features are generated for TD-SVs using audio data from spoken utterances during interactions with an automated assistant.
- The system determines if recognized terms in the spoken utterance correspond to the TD-SV and if the authentication measure satisfies a threshold.
- Speaker features are utilized to authenticate spoken utterances for the user.
Potential Applications: - Security systems for voice authentication - Call center authentication processes - Automated customer service interactions
Problems Solved: - Enhancing security through voice authentication - Streamlining authentication processes - Improving user experience with automated systems
Benefits: - Increased security measures - Efficient authentication processes - Enhanced user experience with automated assistants
Commercial Applications: Title: "Voice Authentication System for Automated Assistants" This technology can be used in various industries such as banking, telecommunications, and healthcare for secure and efficient user authentication processes.
Questions about the technology: 1. How does this technology improve user security during interactions with automated systems? 2. What are the potential drawbacks of using speaker features for authentication in automated systems?
Frequently Updated Research: Research on improving speaker recognition accuracy and efficiency in automated systems is ongoing, with a focus on enhancing user experience and security measures.
Original Abstract Submitted
implementations relate to automatic generation of speaker features for each of one or more particular text-dependent speaker verifications (td-svs) for a user. implementations can generate speaker features for a particular td-sv using instances of audio data that each capture a corresponding spoken utterance of the user during normal non-enrollment interactions with an automated assistant via one or more respective assistant devices. for example, a portion of an instance of audio data can be used in response to: (a) determining that recognized term(s) for the spoken utterance captured by that the portion correspond to the particular td-sv; and (b) determining that an authentication measure, for the user and for the spoken utterance, satisfies a threshold. implementations additionally or alternatively relate to utilization of speaker features, for each of one or more particular td-svs for a user, in determining whether to authenticate a spoken utterance for the user.
