This GitHub repository provides for Two Microphone DOA estimation on Android smartphone platform. The example app provided here is for hearing improvement studies.
Abstract: In this paper, we present an improved version of a Speech source Iocalization method for Direction of Arrival (DOA) estimation using only two microphones. We also present a real-time Android application on a latest smartphone to help improve the spatial awareness of hearing impaired users. Unlike earlier methods, the proposed method is computationally more efficient and fully adaptive to dynamically changing background noise. We compare the performance of proposed method with similar earlier methods and demonstrate significantly lower DOA estimation errors as well as lower computation times. People who find it difficult to localize speech sources during group conversations or social activities can use the `easy-to-use' Android application. The proposed implementation does not need any additional hardware or external microphone attachments, and can run on any dual-microphone device, such as a smartphone or tablet.
You can find the manuscript for this GitHub repository : https://ieeexplore.ieee.org/document/8512318
A User's Guide is provided describing the real-time implementation on Android smartphone platforms.
- add requirements
The codes are licensed under open-source MIT license.
For any utilization of the code content of this repository, one of the following books needs to get cited by the user:
A. Ganguly, A. Küçük and I. Panahi, "Real-time Smartphone application for improving spatial awareness of Hearing Assistive Devices," 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, 2018, pp. 433-436, doi: 10.1109/EMBC.2018.8512318.
This work was supported in part by the National Institute of the Deafness and Other Communication Disorders (NIDCD) of the National Institutes of Health (NIH) under Award 1R01DC015430-04. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent