Hye-jin Shim
Scholar

Hye-jin Shim

Google Scholar ID: MSIvlNoAAAAJ
Carnegie Mellon University
Speaker recognitionAnti-spoofingSpeech processingAcoustic modeling
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,954
 
H-index
21
 
i10-index
36
 
Publications
20
 
Co-authors
0
 
Contact
CVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
11 items
ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling
2026
Cited
0
The CMU-AIST submission for the ICME 2025 Audio Encoder Challenge
2026
Cited
0
Geolocation-Aware Robust Spoken Language Identification
2025
Cited
0
WildSpoof Challenge Evaluation Plan
2025
Cited
0
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
2025
Cited
0
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
2025
Cited
0
ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
2025
Cited
0
VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music
arXiv.org · 2024
Cited
4
Resume
Background
  • Research interests: audio anti-spoofing, speaker verification. Currently a postdoctoral researcher at Carnegie Mellon University.
Miscellany
  • Community Engagements: Conference Review (Interspeech, ICASSP, Odyssey, ASRU, SLT), Journal Review (CSL, TASLP, Speech Communications, Digital Signal Processing, Pattern Recognition Letters, Applied Acoustics), Challenge Organizer (ASVspoof5 Challenge, Spoofing-Aware Speaker Verification Challenge), Session Chair (Spoofing-Aware Speaker Verification Special Session, Interspeech)