This letter explores a least absolute shrinkage and selection operator- (Lasso-) based beamforming algorithm for a sparse cylindrically baffled speaker array, which can be used for low-cost multi-channel surround sound reproduction. The proposed method exploits the inherent sparsity of the Lasso algorithm, and achieves both narrower beamwidth and a smaller side lobe in comparison with existing algorithms in both simulation and experiment. In addition, further study on the dependency of operating speaker sparsity on regularization parameter enables user preference-based adjustment in practice.