Spatial Covariant Matrix based Learning for DOA Estimation in Spherical Harmonics Domain

Yuan Z, Gao S, Wu X, Qu T. Spatial Covariant Matrix based Learning for DOA Estimation in Spherical Harmonics Domain. In: Convention Paper. Audio Engineering Society; 2024. Paper 10701. Available from: https://aes.org/publications/elibrary-page/?id=22514

@inproceedings{Yuan2024_22514,
  author = {Yuan, Zeyu and Gao, Shan and Wu, Xihong and Qu, Tianshu},
  title = {{Spatial Covariant Matrix based Learning for DOA Estimation in Spherical Harmonics Domain}},
  note = {Paper 10701},
  year = {2024},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=22514}
}

TY  - CPAPER
TI  - Spatial Covariant Matrix based Learning for DOA Estimation in Spherical Harmonics Domain
AU  - Yuan, Zeyu
AU  - Gao, Shan
AU  - Wu, Xihong
AU  - Qu, Tianshu
M1  - Paper 10701
PY  - 2024
DA  - 2024/06/06
UR  - https://aes.org/publications/elibrary-page/?id=22514
PB  - Audio Engineering Society
LA  - en
AB  - Direction of arrival (DoA) estimation in complex environments is a challenging task. The traditional methods suffer from invalidity under low signal-to-noise ratio (SNR) and reverberation conditions, and the data-driven methods lack of generalization to unseen data types. In this paper we propose a robust DoA estimation approach by combining the two methods above. To focus on spatial information modeling, the proposed method directly uses the compressed covariance matrix of the first-order ambisonics (FOA) signal as input, while only white noise is used during training. To adapt to different characteristics of FOA signals in different frequency bands, our method estimates DoA in different frequency bands by particular models, and the subband results are finally integrated together. Experiments are carried out on both simulated and measured datasets, and the results show the superiority of the proposed method than existing baselines under complex conditions and the scalability for unseen data types.
ER  -