Speaker Identification via Voice Feature Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing complexity of user interfaces in electronic devices, such as mobile radiotelephones, makes it difficult for users to navigate and identify parties due to the need to access multiple menu levels for simple tasks like changing settings or recognizing individuals during calls.
Innovation Solution
A method and device that associate first data identifying a party with second data characterizing a feature, such as voice or facial characteristics, derived from a telephone call, allowing for future recognition without requiring user input, using a transceiver, storage device, and processor to store and compare data for identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of features is increased in a single electronic device, then the functionality and versatility of the device is improved, but the user interface complexity increases making it difficult to learn and use
Solution Approach 1:
The device automatically performs speaker identification by analyzing voice characteristics during telephone calls without requiring user intervention. The system self-updates its database of speaker features and automatically associates them with contact information, eliminating the need for users to manually navigate complex menus to set up identification profiles.
Solution Approach 2:
The system pre-processes and stores voice characteristics during telephone calls before they are needed for identification. By continuously collecting and analyzing audio data in advance, the device builds a database of speaker features that can be quickly matched against incoming calls, avoiding the need for users to perform setup actions at the moment of identification.
2Reliability
If manual speaker identification setup is required, then the device can identify speakers, but the user must navigate complex menu systems to change settings or add identification data
Solution Approach 1:
The device automatically performs speaker identification by analyzing voice characteristics during telephone calls without requiring user intervention. The system self-updates its database of speaker features and automatically associates them with contact information, eliminating the need for users to manually navigate complex menus to set up identification profiles.
Solution Approach 2:
The system uses voice characteristics as an intermediary to automatically link speaker identity with contact information. Instead of requiring users to manually input or select identification data through menus, the system analyzes audio features during calls and uses these characteristics as a key to automatically associate and retrieve contact information, simplifying the user interaction process.
Data Source
AI summary
Embodiments of the present invention provide a method of associating first data identifying a first party with second data to allow future recognition of the first party, including the steps of: conducting a telephone call with the first party; storing second data derived from the telephone call with the first party, the second data being different to the first data and characterizing a feature of the first party to allow future recognition of the first party; and associating the first data with the second data.