5 papers
Multi-Task Multi-Frame Visual Piano Transcription
Yonghyun Kim, Hoyeol Sohn, Juhan Nam +1
Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extende…
Audio-Based Pedestrian Detection in the Presence of Vehicular Noise
Yonghyun Kim, Chaeyeon Han, Akash Sarode +3
Audio-based pedestrian detection is a challenging task and has, thus far, only been explored in noise-limited environments. We present a new dataset, results, and a detailed analys…
Two Web Toolkits for Multimodal Piano Performance Dataset Acquisition and Fingering Annotation
Junhyung Park, Yonghyun Kim, Joonhyung Bae +4
Piano performance is a multimodal activity that intrinsically combines physical actions with the acoustic rendition. Despite growing research interest in analyzing the multimodal n…
PianoVAM: A Multimodal Piano Performance Dataset
Yonghyun Kim, Junhyung Park, Joonhyung Bae +4
The multimodal nature of music performance has driven increasing interest in data beyond the audio domain within the music information retrieval (MIR) community. This paper introdu…
Towards Robust Transcription: Exploring Noise Injection Strategies for Training Data Augmentation
Yonghyun Kim, Alexander Lerch
Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains la…