Scholar
Jee-weon Jung
Google Scholar ID: A5OcLdAAAAAJ
Apple, Carnegie Mellon University
Speaker recognition
Anti-spoofing
Speaker diarization
Speech processing
Deep learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,459
H-index
28
i10-index
59
Publications
20
Co-authors
75
list available
Contact
CV
Open ↗
GitHub
Open ↗
Publications
10 items
Which Data Matter? Embedding-Based Data Selection for Speech Recognition
2026
Cited
0
WildSpoof Challenge Evaluation Plan
2025
Cited
0
Chain-of-Thought Training for Open E2E Spoken Dialogue Systems
2025
Cited
0
SEED: Speaker Embedding Enhancement Diffusion Model
2025
Cited
0
ESPnet-Codec: Comprehensive Training and Evaluation of Neural Codecs For Audio, Music, and Speech
Spoken Language Technology Workshop · 2024
Cited
3
SpoofCeleb: Speech Deepfake Detection and SASV in the Wild
IEEE Open Journal of Signal Processing · 2024
Cited
1
Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
arXiv.org · 2024
Cited
0
Text-To-Speech Synthesis In The Wild
arXiv.org · 2024
Cited
1
Load more
Resume (English only)
Academic Achievements
1st place, DCASE 2024 Challenge Task 6 (Automated Audio Captioning, AAC), 2024
1st place, DCASE 2023 Challenge Task 6-a (Automated Audio Captioning, AAC), 2023
3rd place, Third DIHARD Speech Diarisation Challenge (Track 1 Core, Speaker Diarization, SD), 2021
Published over 90 papers in leading academic venues, including:
“AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks” (ICASSP 2022)
“RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification” (INTERSPEECH 2019)
“SASV 2022: The First Spoofing-Aware Speaker Verification Challenge” (INTERSPEECH 2022)
“Knowledge Distillation in Acoustic Scene Classification” (IEEE Access, 2020)
“Graph Attention Networks for Speaker Verification” (ICASSP 2021)
Co-authors
75 total
Hye-jin Shim
Carnegie Mellon University
Co-author 2
Ha-Jin Yu
School of Computer Science, University of Seoul
Joon Son Chung
KAIST
Shinji Watanabe
Carnegie Mellon University
Nicholas Evans
Professor, Audio Security and Privacy, EURECOM, France
Co-author 7
Hemlata Tak
Research Scientist, Pindrop
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up