3 papers
cs.LG2020
Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing
Eric Guizzo, Tillman Weyde, Giacomo Tarroni
We introduce the novel concept of anti-transfer learning for speech processing with convolutional neural networks. While transfer learning assumes that the learning process for a t…
cs.SD2020
A Neural Network Based Framework for Archetypical Sound Synthesis
Eric Guizzo, Alberto Novello
This paper describes a preliminary approach to algorithmically reproduce the archetypical structure adopted by humans to classify sounds. In particular, we propose an approach to p…
eess.AS2020
Multi-Time-Scale Convolution for Emotion Recognition from Speech Audio Signals
Eric Guizzo, Tillman Weyde, Jack Barnett Leveson
Robustness against temporal variations is important for emotion recognition from speech audio, since emotion is ex-pressed through complex spectral patterns that can exhibit signif…