2 papers
eess.AS2020
Vocoder-free End-to-End Voice Conversion with Transformer Network
June-Woo Kim, Ho-Young Jung, Minho Lee
Mel-frequency filter bank (MFB) based approaches have the advantage of learning speech compared to raw spectrum since MFB has less feature size. However, speech generator with MFB…
cs.LG2018
End-to-end Multimodal Emotion and Gender Recognition with Dynamic Joint Loss Weights
Myungsu Chae, Tae-Ho Kim, Young Hoon Shin +2
Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of…