47 citations · 146 across the 17 of their papers we have counts for
18 papers
A Foundation Model for Music Informatics
Minz Won, Yun-Ning Hung, Duc Le
This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we c…
Mel-Band RoFormer for Music Source Separation
Ju-Chiang Wang, Wei-Tsung Lu, Minz Won
Recently, multi-band spectrogram-based approaches such as Band-Split RNN (BSRNN) have demonstrated promising results for music source separation. In our recent work, we introduce t…
Scaling Up Music Information Retrieval Training with Semi-Supervised Learning
Yun-Ning Hung, Ju-Chiang Wang, Minz Won +1
In the era of data-driven Music Information Retrieval (MIR), the scarcity of labeled data has been one of the major concerns to the success of an MIR task. In this work, we leverag…
Textless Speech-to-Music Retrieval Using Emotion Similarity
SeungHeon Doh, Minz Won, Keunwoo Choi +1
We introduce a framework that recommends music based on the emotions of speech. In content creation and daily life, speech contains information about human emotions, which can be e…
Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training
Kin Wai Cheuk, Keunwoo Choi, Qiuqiang Kong +5
In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is capable of transcribing, recognizing, and separating multiple musical instruments from…
Toward Universal Text-to-Music Retrieval
SeungHeon Doh, Minz Won, Keunwoo Choi +1
This paper introduces effective design choices for text-to-music retrieval systems. An ideal text-based retrieval system would support various input queries such as pre-defined tag…