Trained Model for Sound Volume Balance in Virtual Space
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sound processing technologies fail to effectively adjust the volume balance of multiple performers in a virtual space, leading to imbalanced audio experiences.
Innovation Solution
A method and apparatus for sound processing that utilize a trained model to learn the relationship between sound signals and volume adjustment parameters for each performer, allowing for real-time adjustment and mixing of sound volumes in a virtual space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual volume adjustment methods are used for multiple performers in virtual space, then operation simplicity is maintained, but volume balance adjustment precision deteriorates
Solution Approach 1:
The system performs automatic volume balance adjustment without requiring manual operation. The volume adjustment unit automatically adjusts the volume of each performer's sound signal based on spatial position and distance information, eliminating the need for manual volume control while achieving precise volume balance.
Solution Approach 2:
The system changes volume parameters automatically based on spatial parameters. By calculating distance between performers and listeners, and determining spatial positions in the virtual space, the system dynamically adjusts volume parameters to achieve optimal volume balance without manual intervention.
2Manufacturing precision
If automated volume adjustment using trained models is implemented, then volume balance precision is improved, but device complexity increases
Solution Approach 1:
The system introduces a trained model as an intermediary between spatial information and volume adjustment decisions. The model learns optimal volume adjustment strategies from training data and applies them automatically, bridging the gap between simple spatial parameters and complex volume balance requirements.
Solution Approach 2:
The system performs preliminary training of the volume adjustment model using training datasets before actual use. This preliminary action allows the model to learn optimal volume adjustment patterns in advance, enabling accurate automatic adjustment during actual operation without requiring complex real-time calculations.
3Reliability
If spatial position-based volume adjustment is applied, then volume balance appropriateness is improved, but calculation complexity increases
Solution Approach 1:
The system replaces complex mechanical volume adjustment calculations with a trained machine learning model. Instead of manually calculating optimal volumes based on spatial relationships, the model has already learned these relationships during training, simplifying the runtime calculation process while maintaining accuracy.
Data Source
AI summary
A method of processing sound includes arranging objects of a plurality of performers in a virtual space. The method also includes receiving a plurality of sound signals respectively corresponding to the plurality of performers. The method also includes obtaining, using a trained model, sound volume adjustment parameters respectively for the plurality of performers. The trained model is trained to learn a relationship between each sound signal, among the plurality of sound signals, that corresponds to each performer of the plurality of performers and each sound volume adjustment parameter, among the sound volume adjustment parameters, that corresponds to the each sound signal. The method also includes adjusting and mixing sound volumes respectively of the plurality of sound signals based on the sound volume adjustment parameters obtained using the trained model.