A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments
Acoustic source localization in the spherical harmonic domain with reverberation has hitherto not been extensively investigated. Moreover, deep learning frameworks have been utilized to estimate the direction-of-arrival (DOA) with spherical microphone arrays under environments with reverberation and...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4278 |
| _version_ | 1827673332133134336 |
|---|---|
| author | Qinghua Huang Weilun Fang |
| author_facet | Qinghua Huang Weilun Fang |
| author_sort | Qinghua Huang |
| collection | DOAJ |
| description | Acoustic source localization in the spherical harmonic domain with reverberation has hitherto not been extensively investigated. Moreover, deep learning frameworks have been utilized to estimate the direction-of-arrival (DOA) with spherical microphone arrays under environments with reverberation and noise for low computational complexity and high accuracy. This paper proposes three different covariance matrices as the input features and two different learning strategies for the DOA task. There is a progressive relationship among the three covariance matrices. The second matrix can be obtained by processing the first matrix and it effectively filters out the effects of the microphone array and mode strength to some extent. The third matrix can be obtained by processing the second matrix and it further efficiently removes information irrelevant to location information. In terms of the strategies, the first strategy is a regular learning strategy, while the second strategy is to split the task into three parts to be performed in parallel. Experiments were conducted both on the simulated and real datasets to show that the proposed method has higher accuracy than the conventional methods and lower computational complexity. Thus, the proposed method can effectively resist reverberation and noise. |
| first_indexed | 2024-03-10T04:23:18Z |
| format | Article |
| id | doaj.art-dd96b71b5d1b407db81eab8ecaa196b3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:23:18Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-dd96b71b5d1b407db81eab8ecaa196b32023-11-23T07:46:47ZengMDPI AGApplied Sciences2076-34172022-04-01129427810.3390/app12094278A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant EnvironmentsQinghua Huang0Weilun Fang1Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, ChinaKey Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200444, ChinaAcoustic source localization in the spherical harmonic domain with reverberation has hitherto not been extensively investigated. Moreover, deep learning frameworks have been utilized to estimate the direction-of-arrival (DOA) with spherical microphone arrays under environments with reverberation and noise for low computational complexity and high accuracy. This paper proposes three different covariance matrices as the input features and two different learning strategies for the DOA task. There is a progressive relationship among the three covariance matrices. The second matrix can be obtained by processing the first matrix and it effectively filters out the effects of the microphone array and mode strength to some extent. The third matrix can be obtained by processing the second matrix and it further efficiently removes information irrelevant to location information. In terms of the strategies, the first strategy is a regular learning strategy, while the second strategy is to split the task into three parts to be performed in parallel. Experiments were conducted both on the simulated and real datasets to show that the proposed method has higher accuracy than the conventional methods and lower computational complexity. Thus, the proposed method can effectively resist reverberation and noise.https://www.mdpi.com/2076-3417/12/9/4278direction-of-arrivalspherical microphone arraycovariance matrixconvolutional neural network |
| spellingShingle | Qinghua Huang Weilun Fang A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments Applied Sciences direction-of-arrival spherical microphone array covariance matrix convolutional neural network |
| title | A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments |
| title_full | A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments |
| title_fullStr | A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments |
| title_full_unstemmed | A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments |
| title_short | A Deep Learning Method for DOA Estimation with Covariance Matrices in Reverberant Environments |
| title_sort | deep learning method for doa estimation with covariance matrices in reverberant environments |
| topic | direction-of-arrival spherical microphone array covariance matrix convolutional neural network |
| url | https://www.mdpi.com/2076-3417/12/9/4278 |
| work_keys_str_mv | AT qinghuahuang adeeplearningmethodfordoaestimationwithcovariancematricesinreverberantenvironments AT weilunfang adeeplearningmethodfordoaestimationwithcovariancematricesinreverberantenvironments AT qinghuahuang deeplearningmethodfordoaestimationwithcovariancematricesinreverberantenvironments AT weilunfang deeplearningmethodfordoaestimationwithcovariancematricesinreverberantenvironments |