Directional Audio Separation for Meeting Recordings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In meetings with multiple participants, existing electronic devices struggle to accurately identify and separate individual speakers' voices, making it difficult to distinguish between speakers as the number of participants increases.
Innovation Solution
An electronic device equipped with multiple microphones and a directional recognition algorithm that classifies sound directions into sectors, allowing for the generation and reproduction of audio files with directional information, enabling selective playback of specific speakers' voices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple microphones are used to record meeting contents, then the ability to capture multiple speakers' voices is improved, but the difficulty of identifying and separating individual speakers increases
Solution Approach 1:
The patent segments the audio recording by associating each microphone's recording with its specific spatial direction. The controller divides the meeting recording into multiple audio files, each corresponding to a specific direction from which a speaker's voice was captured. This segmentation allows individual speakers to be identified and separated based on the directional information from different microphones, resolving the difficulty of distinguishing speakers when multiple microphones are used.
2Quantity of substance
If the number of meeting participants increases, then the comprehensiveness of meeting coverage is improved, but the ability to identify which user speaks deteriorates
Solution Approach 1:
The patent introduces a spatial dimension to speaker identification by capturing the directional information from which each voice originates. Instead of relying solely on temporal or spectral analysis, the system uses the spatial dimension (direction) provided by multiple microphones positioned at different locations. This additional dimension enables precise identification of which participant is speaking, even when the number of participants increases, as each speaker can be distinguished by the direction from which their voice is captured.
Data Source
AI summary
An electronic device is provided. The electronic device includes a controller configured to execute one or more modules, an audio reproduction module configured to reproduce an audio file including reproduction sections, each of the reproduction sections comprising audio data and directional information, a display configured to display selectable objects corresponding to the directional information, and an audio control module configured to determine whether to reproduce audio data corresponding the directional information based on an input for selecting one of the selectable objects.