Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation
Over the past decade, neural networks have been widely used for direction-of-arrival (DoA) estimation owing to their high accuracy in noisy and reverberant environments. Classes of singular-model classifiers generally correspond to discretized DoA candidate angles, which in the case of a three-dimen...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9913958/ |
| _version_ | 1811182610654691328 |
|---|---|
| author | Israel Mendoza-Velazquez Hector Perez-Meana Yoichi Haneda |
| author_facet | Israel Mendoza-Velazquez Hector Perez-Meana Yoichi Haneda |
| author_sort | Israel Mendoza-Velazquez |
| collection | DOAJ |
| description | Over the past decade, neural networks have been widely used for direction-of-arrival (DoA) estimation owing to their high accuracy in noisy and reverberant environments. Classes of singular-model classifiers generally correspond to discretized DoA candidate angles, which in the case of a three-dimensional estimation, are bounded by the grid derived from uniform sampling over the unit sphere. Motivated by this, we propose an ensemble learning approach for classification tasks to improve estimation accuracy, as the ensemble criterion outperforms the individual criterion. First, individual networks that make up the ensemble differ slightly by grid rotation according to the Euler rotation theorem to complement discrete directional information. Score fusion was performed in the spherical harmonic domain for a more stable ensemble classification because the grid rotation also involves an angular mismatch. Moreover, to achieve a more accurate DoA estimation, interpolation over the fused scores was performed. Performance analysis and a comparison of state-of-the-art parametric and deep learning-based methods in several acoustic situations were conducted to determine the accuracy of the ensemble and to analyze the gradual angular error reduction as a function of noise and reverberation levels as more networks were added. |
| first_indexed | 2024-04-11T09:33:31Z |
| format | Article |
| id | doaj.art-a90bbbfde6ea4c0097408cbd87dcf3e9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T09:33:31Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a90bbbfde6ea4c0097408cbd87dcf3e92022-12-22T04:31:46ZengIEEEIEEE Access2169-35362022-01-011010818510819310.1109/ACCESS.2022.32130319913958Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival EstimationIsrael Mendoza-Velazquez0https://orcid.org/0000-0002-5888-2435Hector Perez-Meana1Yoichi Haneda2https://orcid.org/0000-0001-8477-6575Graduate School of Informatics, The University of Electro-Communications, Tokyo, JapanESIME Culhuacan, Instituto Politecnico Nacional, Mexico City, MexicoGraduate School of Informatics, The University of Electro-Communications, Tokyo, JapanOver the past decade, neural networks have been widely used for direction-of-arrival (DoA) estimation owing to their high accuracy in noisy and reverberant environments. Classes of singular-model classifiers generally correspond to discretized DoA candidate angles, which in the case of a three-dimensional estimation, are bounded by the grid derived from uniform sampling over the unit sphere. Motivated by this, we propose an ensemble learning approach for classification tasks to improve estimation accuracy, as the ensemble criterion outperforms the individual criterion. First, individual networks that make up the ensemble differ slightly by grid rotation according to the Euler rotation theorem to complement discrete directional information. Score fusion was performed in the spherical harmonic domain for a more stable ensemble classification because the grid rotation also involves an angular mismatch. Moreover, to achieve a more accurate DoA estimation, interpolation over the fused scores was performed. Performance analysis and a comparison of state-of-the-art parametric and deep learning-based methods in several acoustic situations were conducted to determine the accuracy of the ensemble and to analyze the gradual angular error reduction as a function of noise and reverberation levels as more networks were added.https://ieeexplore.ieee.org/document/9913958/Convolutional recurrent neural networksspherical harmonicsthree-dimensional microphone arraysdirection of arrivalensemble learning |
| spellingShingle | Israel Mendoza-Velazquez Hector Perez-Meana Yoichi Haneda Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation IEEE Access Convolutional recurrent neural networks spherical harmonics three-dimensional microphone arrays direction of arrival ensemble learning |
| title | Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation |
| title_full | Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation |
| title_fullStr | Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation |
| title_full_unstemmed | Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation |
| title_short | Ensemble Learning Approach With Class Rotation for Three-Dimensional Classification on Direction-of-Arrival Estimation |
| title_sort | ensemble learning approach with class rotation for three dimensional classification on direction of arrival estimation |
| topic | Convolutional recurrent neural networks spherical harmonics three-dimensional microphone arrays direction of arrival ensemble learning |
| url | https://ieeexplore.ieee.org/document/9913958/ |
| work_keys_str_mv | AT israelmendozavelazquez ensemblelearningapproachwithclassrotationforthreedimensionalclassificationondirectionofarrivalestimation AT hectorperezmeana ensemblelearningapproachwithclassrotationforthreedimensionalclassificationondirectionofarrivalestimation AT yoichihaneda ensemblelearningapproachwithclassrotationforthreedimensionalclassificationondirectionofarrivalestimation |