Junghyun Koo

Junghyun Koo

Auto-generated profile, based on publicly available information

Junghyun Koo

Mitsubishi Electric Research Laboratories, Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 January 2025 in IEEE Open Journal of Signal Processing
Verified
Journal Article
Open access
JKJunghyun Koo
Junghyun Koo
GWGordon Wichern
Gordon Wichern
FGFrançois G. Germain
François G. Germain
SKSameer Khurana
Sameer Khurana
JRJonathan Le Roux
Jonathan Le Roux
We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for controlling an autoregressive generative music transformer using classifier probes. These simple logistic regression probes are trained on the output of each attention head in the transformer using a small dataset of audio examples both exhibiting and missing a specific musical trait (e.g., the presence/absence of drums, or real/synthetic music). We then steer the attention heads in the probe direction, ensuring the generative model output captures the desired musical trait. Additionally, we monitor the probe output to avoid adding an excessive amount of intervention into the autoregressive generation, which could lead to temporally incoherent music. We validate our results objectively and subjectively for both audio continuation and text-to-music applications, demonstrating the ability to add controls to large generative models for which retraining or even fine-tuning is impractical for most musicians. Audio samples of the proposed intervention approach are available on our http://tinyurl.com/smitin.

26 October 2023
Verified
Conference Paper
Open access
YCYunkee Chae
Yunkee Chae
JKJunghyun Koo
Junghyun Koo
SLSungho Lee
Sungho Lee
KLKyogu Lee
Kyogu Lee