6 papers
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…
Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation
Ryo Terashima, Ryuichi Yamamoto, Eunwoo Song +4
Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are availabl…
Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis
Sang-Hoon Lee, Hyun-Wook Yoon, Hyeong-Rae Noh +2
While generative adversarial networks (GANs) based neural text-to-speech (TTS) systems have shown significant improvement in neural speech synthesis, there is no TTS system to lear…
Audio Dequantization for High Fidelity Audio Generation in Flow-based Neural Vocoder
Hyun-Wook Yoon, Sang-Hoon Lee, Hyeong-Rae Noh +1
In recent works, a flow-based neural vocoder has shown significant improvement in real-time speech generation task. The sequence of invertible flow operations allows the model to c…