30 citations · 42 across the 11 of their papers we have counts for
11 papers
Let There Be Sound: Reconstructing High Quality Speech from Silent Videos
Ji-Hoon Kim, Jaehun Kim, Joon Son Chung
The goal of this work is to reconstruct high quality speech from lip motions alone, a task also known as lip-to-speech. A key challenge of lip-to-speech systems is the one-to-many…
CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis
Ji-Hoon Kim, Hong-Sun Yang, Yoon-Cheol Ju +2
While recent text-to-speech (TTS) systems have made remarkable strides toward human-level quality, the performance of cross-lingual TTS lags behind that of intra-lingual TTS. This…
Relation-Aware Language-Graph Transformer for Question Answering
Jinyoung Park, Hyeong Kyu Choi, Juyeon Ko +5
Question Answering (QA) is a task that entails reasoning over natural language contexts, and many relevant works augment language models (LMs) with graph neural networks (GNNs) to…
Two-Step Question Retrieval for Open-Domain QA
Yeon Seonwoo, Juhee Son, Jiho Jin +4
The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle thi…
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
Jisoo Mok, Byunggook Na, Ji-Hoon Kim +2
In Neural Architecture Search (NAS), reducing the cost of architecture evaluation remains one of the most crucial challenges. Among a plethora of efforts to bypass training of each…
GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints
Ji-Hoon Kim, Sang-Hoon Lee, Ji-Hyun Lee +2
Few-shot speaker adaptation is a specific Text-to-Speech (TTS) system that aims to reproduce a novel speaker's voice with a few training data. While numerous attempts have been mad…
Weakly Supervised Pre-Training for Multi-Hop Retriever
Yeon Seonwoo, Sang-Woo Lee, Ji-Hoon Kim +2
In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question de…
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Ji-Hoon Kim, Sang-Hoon Lee, Ji-Hyun Lee +1
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This d…
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…
Context-Aware Answer Extraction in Question Answering
Yeon Seonwoo, Ji-Hoon Kim, Jung-Woo Ha +1
Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the corr…
HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks
Heungseok Park, Yoonsoo Nam, Ji-Hoon Kim +1
To mitigate the pain of manually tuning hyperparameters of deep neural networks, automated machine learning (AutoML) methods have been developed to search for an optimal set of hyp…