UGC and PGC Audio Classification for Adaptive Playback Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing audio processing systems struggle to differentiate between professionally generated content (PGC) and user-generated content (UGC) due to varying production conditions, leading to suboptimal playback experiences for UGC which often contains noise and reverberation issues.

Innovation Solution

A computer-implemented method that extracts spatial, temporal, and spectral features from audio content to classify it as PGC or UGC, using a classification model trained on labeled data to determine appropriate processing pipelines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single audio processing pipeline is used for all digital audio content, then the system complexity is reduced, but the playback quality for UGC deteriorates due to noise and reverberation issues

Engineering Contradiction:
Improveprocessing system complexityVSAvoidplayback quality
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system dynamically selects between different processing pipelines (PGC pipeline or UGC pipeline) based on the classification result. The processing approach changes adaptively depending on whether the audio content is identified as PGC or UGC, allowing optimal processing for each content type without requiring manual configuration.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes processing parameters by selecting different pipelines with distinct processing characteristics. The PGC pipeline uses parameters optimized for professionally produced content, while the UGC pipeline uses parameters designed to handle noise and reverberation in user-generated content, improving playback quality for each category.

Inventive Principle:
Principle #35Parameter changes

2Loss of time

If digital audio content is processed without classification, then the processing time is reduced, but the playback experience deteriorates due to inappropriate processing

Engineering Contradiction:
Improveprocessing timeVSAvoidplayback experience
Core Design Contradiction:
Loss of timeVSReliability

Solution Approach 1:

The system performs classification before processing to determine the appropriate processing pipeline. This preliminary action enables the system to prepare the correct processing parameters in advance, ensuring that the optimal processing path is selected before the actual audio processing begins, thereby maintaining both efficiency and quality.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If spatial indicators are computed for all frames and frequency bands, then the classification accuracy is improved, but the computational complexity increases

Engineering Contradiction:
Improveclassification accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system computes spatial indicators for only a subset of frames and all frequency bands, rather than for every single frame. This partial computation approach provides sufficient classification accuracy while significantly reducing the computational burden, as the spatial characteristics of audio content are relatively stable over short time periods.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4385012B1Management of professionally generated and user-generated audio content
Publication Date: 2025.07.23 DOLBY LABORATORIES LICENSING CORP
  • EP4385012B1 patent drawingFigure 1~2
  • EP4385012B1 patent drawingFigure 3
  • EP4385012B1 patent drawingFigure 4

AI summary

A system for managing user-generated content (UGC) and professionally generated content (PGC) is disclosed. The system is programmed to receive digital audio data having two channels from a social media platform. The system is programmed to extract spatial features that capture differences in the two channels from the digital audio data. The system is programmed to also extract temporal features, spectral features, and background features from the digital audio data. The system is programmed to then use the extracted features to determine whether to process the digital audio data as UGC or PGC before playback.