Dispersing two-dimensional (2D) graphene sheets in 3D material matrix becomes a promising route to access the exceptional mechanical and electrical properties of individual graphene sheets in bulk quantities for macroscopic applications. However, this is highly restricted by the uncontrolled distribution and orientation of the graphene sheets in 3D structures as well as the weak graphene-matrix bonding and poor load transfer. Here, we propose a previously unreported avenue to embed ordered 2D graphene array into ceramics matrix, where the catastrophic fracture failure mode of brittle ceramics was transformed into stable crack propagation behavior with 250 to 500% improvement in the mechanical toughness. An unprecedentedly low dry sliding friction coefficient of 0.06 in bulk ceramics was obtained mainly due to the inhibition of the microcrack propagation by the ordered 2D graphene array. These unique and low-cost 2D graphene array/ceramic composites may find applications in severe environments with superior structural and functional properties.
Speech separation is a hot topic in multi-speaker speech recognition. The long-term autocorrelation of speech signal sequences is an essential task for speech separation. The keys are effective intra-autocorrelation learning for the speaker’s speech, modelling the local (intra-blocks) and global (intra- and inter- blocks) dependence features of the speech sequence, with the real-time separation of as few parameters as possible. In this paper, the local and global dependence features of speech sequence information are extracted by utilizing different transformer structures. A forward adaptive module of channel and space autocorrelation is proposed to give the separated model good channel adaptability (channel adaptive modeling) and space adaptability (space adaptive modeling). In addition, at the back end of the separation model, a speaker enhancement module is considered to further enhance or suppress the speech of different speakers by taking advantage of the mutual suppression characteristics of each source signal. Experiments show that the scale-invariant signal-to-noise ratio improvement (SI-SNRi) of the proposed separation network on the public corpus WSJ0-2mix achieves better separation performance compared with the baseline models. The proposed method can provide a solution for speech separation and speech recognition in multi-speaker scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.