In this paper we propose a fully Bayesian hierarchical model for multi-speaker direction of arrival (DoA) estimation and separation in noisy environments, utilizing the W-disjoint orthogonality property of the speech sources. Our probabilistic approach employs a mixture of Gaussians formulation with centroids associated with a grid of candidate speakers' DoAs. The hierarchical Bayesian model is established by attributing priors to the various parameters. We then derive a variational Expectation-Maximization algorithm that estimates the DoAs by selecting the most probable candidates, and separates the speakers using a variant of the multichannel Wiener filter that takes into account the responsibility of each candidate in describing the received data. The proposed algorithm is evaluated using real room impulse responses from a freely-available database, in terms of both DoA estimates accuracy and separation scores. It is shown that the proposed method outperforms competing methods.
|Title of host publication||Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020|
|Publisher||IEEE Computer Society|
|State||Published - Sep 2020|
|Event||30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 - Virtual, Espoo, Finland|
Duration: 21 Sep 2020 → 24 Sep 2020
|Name||IEEE International Workshop on Machine Learning for Signal Processing, MLSP|
|Conference||30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020|
|Period||21/09/20 → 24/09/20|
Bibliographical notePublisher Copyright:
© 2020 IEEE.
- Audio source separation
- DoA estimation
- Mixture of Gaussians
- Variational EM
- W-disjoint orthogonality