“…In the context of speech processing, sparse recovery has already been studied for robust speech recognition [18], [19], [20], enhanced acoustic modeling [14], [15] as well as spoken query detection [13], [21], [22]. In our earlier work [13], we cast the query detection problem as subspace detection between query and non-query speech where the corresponding subspaces are modeled through dictionary learning for sparse representation. Given these dictionaries, detection of each frame is performed based on the ratio of the two corresponding sparse representation reconstruction errors, and the frame-level decisions are accumulated by counting the continuous number of frames detected as the query.…”