Junghyun Koo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Junghyun Koo has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Francois G. Germain
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA
1 shared publication - Gordon Wichern
Mitsubishi Electric Research Laboratories (MERL) Cambridge MA USA
1 shared publication - Jonathan Le Roux
Mitsubishi Electric Research Laboratories (MERL) Cambridge MA USA
1 shared publication - Kyogu Lee
Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Republic of Korea
1 shared publication Sameer Khurana
Mitsubishi Electric Research Laboratories, Cambridge, MA, USA
1 shared publication- Sungho Lee
Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 6, 266-275
SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers
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.
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 6, 266-275
Open AccessSMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers
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.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2362-2370
Exploiting Time-Frequency Conformers for Music Audio Enhancement
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2362-2370
Open AccessExploiting Time-Frequency Conformers for Music Audio Enhancement