Dynamic Target Speaker Update in Voice Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices struggle to efficiently update the target speaker in voice recognition systems, especially when the audio signal includes voice signals from multiple users, leading to failed voice recognition and inefficient speaker selection.
Innovation Solution
An electronic device equipped with a voice reception unit, memory, and processor, which uses an artificial intelligence model to acquire a voice signal from an audio signal and identify similarities in user characteristics. When voice recognition fails, the device changes the target speaker by identifying the most similar user based on their characteristic information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If voice recognition is performed using a fixed target speaker in multi-user environments, then the system maintains simple speaker selection logic, but voice recognition accuracy deteriorates when the actual speaker changes
Solution Approach 1:
The patent implements dynamic target speaker updating by comparing acoustic characteristics of received audio signals with registered user profiles in real-time. When a mismatch is detected, the system automatically updates the target speaker identifier, transforming the static speaker selection into a dynamic adaptation process that maintains recognition accuracy in multi-user environments
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring voice recognition results and acoustic characteristic matches. When voice recognition fails or acoustic characteristics diverge from the current target speaker profile, the system receives feedback and updates the target speaker identifier accordingly, creating a closed-loop control system that improves reliability
2Productivity
If the system manually updates target speaker information, then the processing complexity is reduced, but the responsiveness and efficiency of speaker adaptation deteriorates
Solution Approach 1:
The patent enables the system to automatically detect and update target speaker information without manual intervention. The electronic device autonomously compares acoustic characteristics, identifies speaker changes, and updates the target speaker identifier independently, achieving self-service operation that improves productivity while managing complexity through automated algorithms
3Reliability
If the system processes audio signals from all users equally, then fairness is maintained, but voice recognition accuracy for the actual speaker deteriorates
Solution Approach 1:
The patent applies local quality by tailoring the voice recognition processing to match the specific acoustic characteristics of the actual speaker present. Instead of uniform processing for all users, the system dynamically adjusts the target speaker profile to locally optimize recognition accuracy for the current speaker while maintaining the ability to adapt to multiple users
Data Source
AI summary
An electronic device is provided. The electronic device includes: a voice reception unit comprising circuitry, memory storing an artificial intelligence model configured to acquire a voice signal of a user from an audio signal and information on characteristics of a plurality of users, and at least one processor, comprising processing circuitry, individually and/or collectively, configured to: based on an audio signal being received through the voice reception unit, obtain a first audio signal by inputting information on a characteristic of a first user set as a target speaker among the plurality of users and the received audio signal to the artificial intelligence model, based on voice recognition based on the first audio signal failing, identify a similarity between information on a characteristic of a second audio signal excluding the first audio signal among the received audio signals and information on characteristics of remaining users excluding the first user among the plurality of users, and change the target speaker to a second user among the plurality of users.