Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
Topics & Concepts
Computer scienceSpellENCODEGraphFrame (networking)Task (project management)Artificial intelligenceCode (set theory)Node (physics)Term (time)Recurrent neural networkSpeech recognitionPattern recognition (psychology)Machine learningArtificial neural networkTheoretical computer scienceEngineeringGeneSet (abstract data type)ManagementStructural engineeringAnthropologyEconomicsQuantum mechanicsSociologyChemistryBiochemistryTelecommunicationsProgramming languagePhysicsSpeech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis