Adaptive Time Compression for Audio Artifact Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conferencing systems experience audio artifacts due to time compression, particularly when handling network jitter, leading to rough and ghostly sounds, which degrade the user experience.
Innovation Solution
Adaptive time compression techniques that differentiate between silence, voiced speech, and unvoiced speech, and adjust compression based on audio characteristics, such as signal-to-noise ratio and correlation, to minimize artifacts and maintain audio quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If time compression algorithm is used to handle network jitter, then audio latency is reduced, but audio artifacts (rough and ghostly sounds) are introduced
Solution Approach 1:
The patent applies different time compression strategies to different segments of audio based on their characteristics. Voiced speech segments are compressed differently from unvoiced speech segments, and silence periods are handled differently from active speech periods. This local differentiation reduces artifacts by applying compression only where appropriate and using lighter compression for sensitive segments.
Solution Approach 2:
The system dynamically adjusts compression parameters based on real-time audio analysis. The compressor adapts its behavior based on detected speech states (voiced, unvoiced, silence) and network conditions, changing compression ratios and processing characteristics on-the-fly to minimize artifacts while maintaining latency reduction benefits.
2Productivity
If higher compression rates are used to combat network jitter, then more aggressive latency reduction is achieved, but audio quality deteriorates due to increased artifacts
Solution Approach 1:
The patent changes multiple parameters of the time compression algorithm based on audio characteristics and network conditions. Compression ratio, block size, overlap factors, and processing mode are adjusted dynamically to optimize the balance between compression effectiveness and artifact generation for each specific situation.
Solution Approach 2:
Instead of applying maximum compression uniformly, the system applies partial compression selectively. Less aggressive compression is applied to segments where artifacts would be most noticeable (such as voiced speech and silence periods), while more aggressive compression is applied to segments where it can be better tolerated (such as unvoiced speech), achieving overall optimization.
Data Source
AI summary
Various techniques are disclosed for reducing artifacts generated by time compression. by adapting the time compression based on the state of the received audio. The amount of time compression may be bounded based on audio characteristics. Another feature provides a way of determining the most correlated portions of segments of audio. Voiced speech may be distinguished from unvoiced speech. Another feature provides a way of distinguishing between silence, voiced speech, and unvoiced speech. Time compression may be adapted during periods of lengthy silence. Another feature allows for reducing time compression during sensitive portions of the received audio. One or more of these features may be present in different embodiments.