Ji-Hoon Kim
19 papers · 2019–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π§ Keyword Pioneer π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10) π Conference Polyglot (10)
π
Conference Polyglot
(10)
π
Academic Marathon
(6)
π
Cross-Pollinator
(3)
π
Keyword Champion
(2)
π§¬
Topic Evolution
π
Grand Slam
π₯
Unstoppable
(7)
β
The Questioner
π
Century Club
(19)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(87)
Conferences
INTERSPEECH (5)
AAAI (3)
CVPR (3)
ACL (2)
COLING (1)
EMNLP (1)
ICLR (1)
ICML (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Keywords
speech synthesis
(3)
waveform generation
(2)
text-to-speech synthesis
(2)
question answering
(2)
self-supervised learning
(2)
generative adversarial network
(2)
conditional flow matching
(2)
motion estimation
(1)
video generation
(1)
adversarial learning
(1)
voice conversion
(1)
talking face generation
(1)
multimodal learning
(1)
question retrieval
(1)
information bottleneck
(1)
cross-modal learning
(1)
facial animation
(1)
attention mechanism
(1)
neural architecture search
(1)
passage retrieval
(1)
Papers
From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech
CVPR 2025
VoxSim: A perceptual voice similarity dataset
INTERSPEECH 2024
Let There Be Sound: Reconstructing High Quality Speech from Silent Videos
AAAI 2024
Faces that Speak: Jointly Synthesising Talking Face and Speech from Text
CVPR 2024
FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching
INTERSPEECH 2024
Relation-Aware Language-Graph Transformer for Question Answering
AAAI 2023
FACTSpeech: Speaking a Foreign Language Pronunciation Using Only Your Native Characters
INTERSPEECH 2023
SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search
ICLR 2022
Two-Step Question Retrieval for Open-Domain QA
ACL 2022
Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training?
CVPR 2022
TriniTTS: Pitch-controllable End-to-end TTS without External Aligner
INTERSPEECH 2022
Weakly Supervised Pre-Training for Multi-Hop Retriever
ACL 2021
VoiceMixer: Adversarial Voice Style Mixup
NIPS 2021
Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis
AAAI 2021
Weakly Supervised Pre-Training for Multi-Hop Retriever
IJCNLP 2021
Fre-GAN: Adversarial Frequency-Consistent Audio Synthesis
INTERSPEECH 2021
Context-Aware Answer Extraction in Question Answering
EMNLP 2020
Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model
COLING 2020
Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty
ICML 2019