Video Telephony Voice Output Control via Face Distance Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video telephony systems face challenges in providing smooth calls due to surrounding noises and the difficulty in maintaining optimal video transmission quality, as they do not effectively account for the distance between the user and the terminal, leading to suboptimal voice signal output levels.
Innovation Solution
A method and apparatus that automatically control the output level of a received voice signal in video telephony by processing input and received image signals to extract face region size information, estimating the distance between the user and the terminal, and adjusting the voice signal output based on this information to mitigate noise interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If the user's face is placed apart from the camera by a predetermined distance or longer for video telephony, then the video transmission quality is improved, but surrounding noises are likely to be transmitted and received, preventing smooth calls
Solution Approach 1:
The patent introduces an intermediary noise cancellation mechanism that processes the audio signal between the user and the communication system. The system estimates the distance between the user and terminal, then applies noise cancellation algorithms to remove surrounding noises from the audio signal, allowing clear communication even when the user is at a distance from the camera
Solution Approach 2:
The patent changes the parameter of audio signal processing by dynamically adjusting noise cancellation strength and voice enhancement levels based on the estimated user distance. As the distance parameter changes, the system modifies audio processing parameters to maintain optimal signal quality while reducing noise interference
2Reliability
If the output level of the received voice signal is increased to overcome surrounding noises, then the voice clarity is improved, but the noise interference and distortion increase
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors the audio signal quality and adjusts the output level dynamically. Based on the estimated distance and detected noise levels, the system feedback-adjusts the voice signal amplification to maintain optimal clarity while preventing noise enhancement and distortion
Solution Approach 2:
The patent replaces simple mechanical volume amplification with sophisticated digital signal processing techniques. Instead of uniformly increasing the output level, the system substitutes advanced noise cancellation and voice enhancement algorithms that selectively process different frequency components to improve clarity without amplifying noise
3Manufacturing precision
If the distance between the user and the terminal is increased for video telephony, then the video quality is improved, but the voice signal output level becomes suboptimal
Solution Approach 1:
The patent applies dynamics by making the voice signal processing parameters adjustable rather than fixed. The system dynamically adapts the output level and noise cancellation strength based on the real-time estimated distance between the user and terminal, ensuring optimal voice signal quality across varying distances while maintaining video quality
Data Source
AI summary
A method and apparatus controls an output level of a voice signal for video telephony by considering the distance between a user and a terminal and surrounding noises. An input image signal and an input voice signal of the user to be used for the video telephony are received at the user's terminal. A received image signal and a received voice signal received from the other party's terminal to which the video telephony is connected, are output on the user's terminal. The user's face region included in the input image signal is extracted. A size information of the extracted face region is checked. A distance information about a distance from the user is checked using the size information. And an output level of the received voice signal is controlled based on the distance information.