You're currently viewing an old version of this dataset. To see the current version, click here.

Attention-based beamformers for multi-channel speech recognition

The proposed 2D Conv-Attention model is compared with a traditional neural beamformer and multi-head attention based model.

Data and Resources

Cite this as

Bhargav Pulugundla, Yang Gao, Brian King, Gokce Keskin, Harish Mallidi, Minhua Wu, Jasha Droppo, Roland Maas (2024). Dataset: Attention-based beamformers for multi-channel speech recognition. https://doi.org/10.57702/9bq5bf7a

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2105.05920
Author Bhargav Pulugundla
More Authors
Yang Gao
Brian King
Gokce Keskin
Harish Mallidi
Minhua Wu
Jasha Droppo
Roland Maas