On Speech Sparsity for Computational Efficiency and Noise Reduction in Hearing Aids

Adrien Llave (1, 2) , Simon Leglaive (1, 2)

1 CentraleSupélec
2 IETR - Institut d'Électronique et des Technologies du numéRique

Beamforming techniques are widely used in hearing aids to improve the signal-to-noise ratio. In a multi-speaker scenario, it is common to assume that the speech signals associated with each speaker do not overlap in the time-frequency domain. This so-called W-disjoint orthogonality assumption allows us to reduce the complexity of the beamforming algorithm. However, its validity decreases in presence of more than two speakers. In this study, we propose a beamforming algorithm relying on a less restrictive assumption regarding the sparsity of speech signals in the time-frequency domain. Its implications over the noise reduction performance and the computational complexity are discussed and compared with the Linearly Constrained Minimum Variance (LCMV) and the Minimum Variance Distortionless Response (MVDR) beamformers. We show that the proposed algorithm improves the noise reduction performance and reduces the computational cost compared to the LCMV beamformer without increasing the artifacts amount unlike the MVDR beamformer.

Mots clés: Beamforming; speech sparsity; noise reduction; hearing aids

Domaines: Complexité [cs.CC]; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Son [cs.SD]

Adrien Llave, Simon Leglaive. On Speech Sparsity for Computational Efficiency and Noise Reduction in Hearing Aids. 13th Asia Pacific Signal and Information Processing Association Annual Summit and Conference, Dec 2021, Tokyo, Japan. ⟨hal-03330307v2⟩