Deep Learning

TTS-by-TTS 2: Data-selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder
Accepted to Interspeech 2022
Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation
Accepted to Interspeech 2022
Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems
Accepted to Interspeech 2022
ESPnet2-TTS: Extending the Edge of TTS Research
Preprint: arXiv:2110.07840 (submitted to ICASSP 2022)