4 papers
Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech
Hyungchan Yoon, Changhwan Kim, Eunwoo Song +2
For personalized speech generation, a neural text-to-speech (TTS) model must be successfully implemented with limited data from a target speaker. To this end, the baseline TTS mode…
Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model
Hoyeon Lee, Hyun-Wook Yoon, Jong-Hwan Kim +1
Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monoling…
Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems
Hyun-Wook Yoon, Ohsung Kwon, Hoyeon Lee +4
This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that requ…
TTS-by-TTS 2: Data-selective augmentation for neural speech synthesis using ranking support vector machine with variational autoencoder
Eunwoo Song, Ryuichi Yamamoto, Ohsung Kwon +6
Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic dat…