Robot Sound Source Elimination via Adaptive Signal Subtraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot systems face interference from their own music signals, which degrade the speech recognition rate due to noise contamination, affecting user experience.
Innovation Solution
A sound source elimination system comprising a pickup unit, sound card drive unit, signal separation unit, sound source elimination unit, and recognition unit, which separates and eliminates interference signals from music played by the robot, ensuring pure speech signals are processed for recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If the robot's HIFI audio system plays music, then the music quality is improved, but the speech signal-to-noise ratio deteriorates due to music signals interfering with speech recognition
Solution Approach 1:
The patent captures the robot's own music output through its speakers using microphones, and then uses signal processing to subtract this self-generated music interference from the speech recognition input. This converts the harmful music interference into a beneficial reference signal that enables effective noise cancellation, allowing both high-quality music playback and accurate speech recognition to coexist.
2Adaptability or versatility
If the robot uses microphones to capture speech, then speech recognition capability is improved, but the recognition rate deteriorates due to music interference from the robot's own audio system
Solution Approach 1:
The patent introduces an intermediary signal processing system that acts as a mediator between the robot's audio output and speech recognition input. The system captures the music reference signal, processes it through adaptive filtering to match the interference characteristics, and subtracts it from the microphone input. This intermediary processing layer enables both music playback and speech recognition to function reliably without mutual interference.
3Adaptability or versatility
If the robot plays music through its audio system, then entertainment function is improved, but the speech signal purity deteriorates causing interference to ASR system
Solution Approach 1:
The patent converts the harmful music interference generated by the robot's own audio system into a beneficial reference signal. By capturing the music output through microphones and using adaptive signal processing to subtract it from the speech recognition input, the system eliminates self-generated noise while maintaining both high-quality music playback and clean speech signals for ASR recognition.
Data Source
AI summary
Provided is a system for a robot to eliminate its own sound source, comprising a sound pickup unit (1) used for acquiring a digital signal having mixed left and right sound channels and outputting same; a sound-card driver unit (2) used for mixing the received reference signal of the robot sound source and the digital signal having mixed left and right sound channels, to form a mixed voice signal, and outputting same; a signal separation unit (3) used for separating the mixed voice signal into a digital signal having mixed left and right sound channels and a reference signal, and determining whether the digital signal having the mixed left and right sound channels contains an interference signal, obtaining a playback signal volume, and outputting same.