Voice Recording System Speaker Identification via Signal Polarity and Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems face challenges in accurately identifying multiple speakers in environments where speakers are positioned similarly to microphones, leading to insufficient accuracy, and require multiple recorders, increasing system complexity and costs.
Innovation Solution
A voice recording system that uses microphones for each speaker, applies unique voice processing such as polarity inversion, signal power adjustment, and delay to two-channel voice signals, and employs an analysis unit to specify speakers by calculating sums or differences of the processed signals, allowing for simple system configuration and accurate speaker identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If directional microphones or microphone arrays are used to specify speakers based on voice arrival direction, then speaker identification capability is provided, but measurement precision deteriorates when speakers exist in similar directions from microphones
Solution Approach 1:
The patent divides the recording function into multiple independent recorders, each dedicated to recording voices from a specific speaker. This segmentation allows each recorder to focus on a single speaker's voice characteristics, thereby maintaining high identification accuracy even when multiple speakers are present in similar directions. The analysis unit then processes recordings from multiple recorders to identify speakers based on their unique voice patterns.
2Measurement precision
If individually recorded voices for each speaker are used to specify speakers, then speaker identification accuracy is improved, but device complexity and system scale increase due to requiring multiple recorders
Solution Approach 1:
The patent makes each recorder universal by enabling it to record voices from multiple speakers simultaneously using omnidirectional microphones. Each recorder is designed to capture all voice signals in its environment, and the analysis unit then processes these universal recordings to identify which speaker is speaking at any given time. This approach maintains speaker identification accuracy while reducing the need for multiple specialized recorders.
3Ease of operation
If multiple recorders are prepared for respective speakers to individually record voices, then speaker specification capability is achieved, but loss of substance increases due to increased costs and maintenance efforts
Solution Approach 1:
The patent employs universal recorders that can serve multiple speakers simultaneously, eliminating the need for dedicated recorders for each speaker. Each recorder captures voices from all speakers in the environment, and the analysis unit processes these recordings to identify speakers based on voice characteristics. This approach significantly reduces the number of recorders needed, thereby lowering system costs and maintenance requirements while maintaining speaker specification capability.
Data Source
AI summary
To provide a method of specifying each of speakers of individual voices, based on recorded voices made by a plurality of speakers, with a simple system configuration, and to provide a system using the method. The system includes: microphones individually provided for each of the speakers; a voice processing unit which gives a unique characteristic to each pair of two-channel voice signals recorded with each of the microphones 10, by executing different kinds of voice processing on the respective pairs of voice signals, and which mixes the voice signals for each channel; and an analysis unit which performs an analysis according to the unique characteristics, given to the voice signals concerning the respective microphones through the processing by the voice processing unit, and which specifies the speaker for each speech segment of the voice signals.