Audio Device System Speech Content Comparison for Noise Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio device systems struggle to effectively suppress noise in complex hearing situations, such as cocktail parties, and require costly and cumbersome solutions like eye trackers or EEG sensors to select the desired speaker.
Innovation Solution
The method involves providing a plurality of sound source signals, selecting a first sound signal based on user interaction or detection, comparing the speech content of the first sound signal with other sound source signals, and selecting the sound source signal most similar to the first sound signal to enhance the audio output while suppressing other sound sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional beamforming or speaker separation techniques are used to suppress noise in complex hearing situations, then speech intelligibility is improved, but device complexity and cost increase due to requiring eye trackers or EEG sensors
Solution Approach 1:
The patent extracts and removes the complex and costly components (eye trackers, EEG sensors) from the audio device system. Instead of using these sophisticated sensors to identify desired speakers, the invention processes audio signals directly through speech content comparison, achieving speaker separation without the need for these extracted components.
Solution Approach 2:
The patent replaces the mechanical/optical sensing systems (eye trackers, EEG sensors) with a signal processing system that compares speech content characteristics. This substitution uses digital signal analysis instead of physical sensing mechanisms, thereby reducing device complexity while maintaining speech intelligibility.
2Measurement precision
If multiple sensors like eye trackers or EEG sensors are added to select the desired speaker, then speaker selection accuracy is improved, but ease of operation deteriorates due to cumbersome setup and usage
Solution Approach 1:
The audio device performs self-service by automatically identifying the desired speaker through speech content comparison without requiring external sensors or user intervention. The system autonomously analyzes audio signals, compares speech characteristics, and selects the target speaker, making the operation simple and intuitive.
Solution Approach 2:
The patent introduces speech content comparison as an intermediary process between audio input and speaker selection. Instead of directly using sensor data from eye trackers or EEG sensors to identify speakers, the system uses speech content characteristics as a mediator to bridge the gap, achieving accurate speaker selection through linguistic analysis rather than physiological sensing.
3Reliability
If speech content comparison is performed to identify the desired speaker, then noise reduction is improved, but processing time increases
Solution Approach 1:
The patent applies partial action by performing speech content comparison only on critical features and parameters rather than analyzing the entire audio signal in detail. By focusing on key speech characteristics that differentiate speakers, the system achieves effective noise reduction while minimizing processing time through selective analysis.
Data Source
AI summary
A method (300) of operating an audio device system in order to provide at least one of improved noise reduction and speech intelligibility and an audio device system (400) adapted to carry out the method.