Seong-Hu Kim

frequency dynamic convolution (2) sound event detection (2) convolutional neural network (2) polyphonic sound (2) audio processing (1) dilated convolution (1) text-independent recognition (1) 2d convolution (1) polyphonic sound detection (1) adaptive convolution (1) embedding extraction (1) neural network architecture (1) frame-level feature (1) speaker embedding (1) speaker recognition (1) pattern recognition (1)