Speech Encoder Parameter Adaptation for External Noise Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech encoders face challenges in maintaining optimal audio quality when switching from a native noise suppressor to a higher quality external noise suppressor, leading to misclassification of speech and noise, which results in suboptimal encoding and inefficient resource utilization.
Innovation Solution
The system adjusts the speech encoder's parameters by receiving and applying a second set of parameters from a high-quality noise suppressor, including signal-to-noise ratio tables and hangover tables, to ensure accurate encoding and efficient resource allocation, thereby improving voice quality and channel capacity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-quality external noise suppressor is introduced to improve noise reduction performance, then noise suppression quality is improved, but the speech encoder misclassifies speech and noise leading to suboptimal encoding
Solution Approach 1:
The patent applies parameter changes by modifying the speech encoder's classification thresholds and parameters to match the output characteristics of the external noise suppressor. This includes adjusting the SNR tables and hangover tables to compensate for the different noise reduction behavior, ensuring the encoder correctly identifies speech and noise segments despite the changed noise profile
Solution Approach 2:
The patent implements feedback mechanisms where the noise suppressor provides information about its processing state and characteristics to the speech encoder. This feedback loop allows the encoder to adapt its classification decisions based on the actual noise suppression applied, preventing misclassification while maintaining optimal encoding
2Productivity
If the speech encoder uses default parameters tuned for the built-in noise suppressor, then encoding is optimized for the native suppressor, but performance degrades when an external noise suppressor is used
Solution Approach 1:
The patent applies dynamics by making the encoder parameters adaptive rather than fixed. The system dynamically adjusts classification thresholds, SNR tables, and hangover parameters based on whether an external noise suppressor is detected and active. This allows the encoder to optimize performance for the native suppressor while automatically adapting to external suppressors without manual reconfiguration
Solution Approach 2:
The patent achieves universality by designing the encoder to function optimally with both the built-in noise suppressor and external noise suppressors. The parameter adjustment mechanisms enable a single encoder implementation to handle multiple noise suppression scenarios, eliminating the need for separate optimization for different suppressor types
3Measurement precision
If noise is aggressively suppressed to improve signal-to-noise ratio, then noise reduction is enhanced, but speech artifacts are introduced and data is wasted
Solution Approach 1:
The patent applies partial action by implementing noise suppression at appropriate levels rather than aggressive over-suppression. The system uses modified classification parameters to identify and suppress only the necessary noise components while preserving speech content. The hangover table adjustments ensure gradual transitions that prevent artifacts while maintaining effective noise reduction
Data Source
AI summary
Provided are methods and systems for improving quality of speech communications. The method may be for improving quality of speech communications in a system having a speech encoder configured to encode a first audio signal using a first set of encoding parameters associated with a first noise suppressor. A method may involve receiving a second audio signal at a second noise suppressor which provides much higher quality noise suppression than the first noise suppressor. The second audio signal may be generated by a single microphone or a combination of multiple microphones. The second noise suppressor may suppress the noise in the second audio signal to generate a processed signal which may be sent to a speech encoder. A second set of encoding parameters may be provided by the second noise suppressor for use by the speech encoder when encoding the processed signal into corresponding data.