Search papers, labs, and topics across Lattice.
3
0
1
36
A clear trade-off between enhancement and spatial fidelity is revealed: beamformer-domain masking achieves the highest speech enhancement scores, while Ambisonics-domain masking better preserves the spatial attributes of the residual interference.
ADEPS can encode spatial audio with zero-shot flexibility across any microphone array, outperforming traditional methods in fidelity and quality.
AmbiDrop's innovative use of Ambisonics allows for superior speech enhancement across arbitrary microphone configurations, outperforming traditional methods constrained by fixed geometries.
