4 papers
Style Modeling for Multi-Speaker Articulation-to-Speech
Miseul Kim, Zhenyu Piao, Jihyun Lee +1
In this paper, we propose a neural articulation-to-speech (ATS) framework that synthesizes high-quality speech from articulatory signal in a multi-speaker situation. Most conventio…
Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking
Jihyun Lee, Chaebin Lee, Yunsu Kim +1
In dialogue state tracking (DST), labeling the dataset involves considerable human labor. We propose a new self-training framework for few-shot generative DST that utilize unlabele…
SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
Jihyun Lee, Gary Geunbae Lee
Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data. In this paper, we introduce an ontology-free…
Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
Se-Yun Um, Jihyun Kim, Jihyun Lee +1
In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with…