An end-to-end audiovisual speech recognition algorithm was proposed. In algorithm. a sparse DBN was constructed by introducing mixed l<sub>1/2</sub>norm and l<sub>1</sub>norm into Deep Belief Network with bottleneck structure to extract the sparse bottleneck features. so as to reduce the dimension of data features. https://missouriquiltcoes.shop/product-category/precut-fused-applique-shapes/