Wearable Audio Speech Isolation in Noisy Proximate Communication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wearable audio devices struggle to accurately communicate speech in noisy environments due to ambient noise interference, as existing noise cancellation technologies fail to isolate speech from ambient noise, leading to reduced audibility and communication efficiency.
Innovation Solution
The audio devices employ multiple microphones to collect audio signals, analyze and compare them to isolate speech from ambient noise, and use wireless communication to transmit the isolated speech to the user, enhancing audibility by attenuating ambient noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If noise cancellation technology is used to reduce ambient noise, then ambient noise is reduced, but speech is also canceled along with the noise
Solution Approach 1:
The audio signal captured by the microphone is segmented into two distinct components: speech signal and ambient noise. The system processes these components separately through signal analysis and comparison, applying different treatments to each component rather than treating the mixed signal as a whole.
Solution Approach 2:
The speech signal is extracted from the mixed audio signal by comparing it with the reference audio signal from the second device. This extraction process separates the desired speech component from the unwanted ambient noise, allowing selective cancellation of only the noise portion.
2Measurement precision
If multiple microphones are used to collect audio signals, then speech isolation accuracy is improved, but device complexity increases
Solution Approach 1:
The system combines the audio signal from the local device's microphone with the reference audio signal from the second device. By merging these two signals and comparing them, the system achieves enhanced speech isolation accuracy without requiring multiple microphones on a single device, thus avoiding increased device complexity.
3Measurement precision
If ambient noise is attenuated through signal processing, then speech audibility is improved, but processing time and computational resources increase
Solution Approach 1:
The second device performs preliminary audio signal collection and preparation in advance, storing the reference audio signal ready for comparison. This preliminary action reduces the real-time processing burden on the first device, as the reference signal is already prepared and can be directly compared with the local microphone signal to quickly isolate speech.
Data Source
AI summary
Techniques, apparatuses, and systems for wireless communication between proximate devices are disclosed. A first microphone on a first wearable audio device of a first user receives first audio signals that include speech from a second user proximate to the first user and ambient noise from an environment surrounding the first wearable audio device. The first audio signals are analyzed to determine primary audio directed to the first user. The primary audio is compared to other audio signals received through wireless communication channels between the first wearable audio device and one or more other wearable audio devices. In doing so, some of the other audio signals are determined to be similar to the primary audio and are thus output to the first wearable audio device. As a result, two users can accurately communicate, even in a noisy environment.