Audio Signal Classification by Shaping Parameter Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio coding systems face challenges in efficiently classifying audio signals to adapt encoding modes or bit rates, particularly in devices with limited processing capacity, such as handheld computers or mobile communication devices.
Innovation Solution
A method for classifying audio signals by estimating shaping parameter values, mapping them to interval estimates, and determining classification decisions based on these values, which allows for efficient selection of coding layers in an embedded layered audio codec.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a typical audio signal classifier is deployed to classify audio signals, then classification accuracy is improved, but processing complexity increases making it infeasible for devices with limited processing capacity
Solution Approach 1:
The patent extracts only the essential shaping parameter from the audio signal for classification purposes, rather than using a comprehensive classifier that analyzes multiple features. This extraction approach maintains classification accuracy while dramatically reducing processing complexity for mobile devices
Solution Approach 2:
The patent uses a simple, computationally inexpensive shaping parameter estimation that can be quickly calculated and discarded, replacing the need for complex, resource-intensive classification algorithms. This disposable approach is optimized for devices with limited processing capacity
2Measurement precision
If complex classification algorithms are used to distinguish between speech and music, then classification accuracy is improved, but encoding efficiency deteriorates due to increased processing time and resources
Solution Approach 1:
The patent extracts a single shaping parameter that captures the essential characteristics needed to distinguish speech from music, eliminating the need for complex multi-feature analysis. This extraction maintains classification accuracy while significantly improving encoding efficiency
Solution Approach 2:
The patent changes the classification approach from using multiple complex parameters to using a single shaping parameter. This parameter transformation enables accurate speech-music distinction while reducing computational burden and improving encoding speed
Data Source
AI summary
An apparatus for classifying an audio signal configured to: estimate at least one shaping parameter value for a plurality of samples of the audio signal; generate at least one audio signal classification value by mapping the at least one shaping parameter value to one of at least two interval estimates; and determine at least one audio signal classification decision based on the at least one audio signal classification value.