Zexu Pan et al.: Muse: Multi-modal target speaker extraction with visual cues. (2020)journals/corr/abs-2010-077752010.07775Muse: Multi-modal target speaker extraction with visual cues.4Zexu Pan1Ruijie Tao2Chenglin Xu3Haizhou Li 00014CoRRCoRRabs/2010.077752020provenance information for RDF data of dblp record 'journals/corr/abs-2010-07775'2020-10-21T19:37:56+0200