Dasaem Jeong

Danbinaerin Han, Rafael Caro Repetto, Dasaem Jeong

In this paper, we introduce a computational analysis of the field recording dataset of approximately 700 hours of Korean folk songs, which were recorded around 1980-90s. Because most of the songs were sung by non-expert musicians without accompaniment, the dataset provides several challenges. To address this challenge, we utilized self-supervised learning with convolutional neural network based on pitch contour, then analyzed how the musical concept of tori, a classification system defined by a specific scale, ornamental notes, and an idiomatic melodic contour, is captured by the model. The experimental result shows that our approach can better capture the characteristics of tori compared to traditional pitch histograms. Using our approaches, we have examined how musical discussions proposed in existing academia manifest in the actual field recordings of Korean folk songs.

Haven Kim, Jongmin Jung, Dasaem Jeong et al.

Lyric translation, a field studied for over a century, is now attracting computational linguistics researchers. We identified two limitations in previous studies. Firstly, lyric translation studies have predominantly focused on Western genres and languages, with no previous study centering on K-pop despite its popularity. Second, the field of lyric translation suffers from a lack of publicly available datasets; to the best of our knowledge, no such dataset exists. To broaden the scope of genres and languages in lyric translation studies, we introduce a novel singable lyric translation dataset, approximately 89\% of which consists of K-pop song lyrics. This dataset aligns Korean and English lyrics line-by-line and section-by-section. We leveraged this dataset to unveil unique characteristics of K-pop lyric translation, distinguishing it from other extensively studied genres, and to construct a neural lyric translation model, thereby underscoring the importance of a dedicated dataset for singable lyric translations.

Danbinaerin Han, Mark Gotham, Dongmin Kim et al.

We introduce a project that revives a piece of 15th-century Korean court music, Chihwapyeong and Chwipunghyeong, composed upon the poem Songs of the Dragon Flying to Heaven. One of the earliest examples of Jeongganbo, a Korean musical notation system, the remaining version only consists of a rudimentary melody. Our research team, commissioned by the National Gugak (Korean Traditional Music) Center, aimed to transform this old melody into a performable arrangement for a six-part ensemble. Using Jeongganbo data acquired through bespoke optical music recognition, we trained a BERT-like masked language model and an encoder-decoder transformer model. We also propose an encoding scheme that strictly follows the structure of Jeongganbo and denotes note durations as positions. The resulting machine-transformed version of Chihwapyeong and Chwipunghyeong were evaluated by experts and performed by the Court Music Orchestra of National Gugak Center. Our work demonstrates that generative models can successfully be applied to traditional music with limited training data if combined with careful design.

Jiwoo Ryu, Hao-Wen Dong, Jongmin Jung et al.

Representing symbolic music with compound tokens, where each token consists of several different sub-tokens representing a distinct musical feature or attribute, offers the advantage of reducing sequence length. While previous research has validated the efficacy of compound tokens in music sequence modeling, predicting all sub-tokens simultaneously can lead to suboptimal results as it may not fully capture the interdependencies between them. We introduce the Nested Music Transformer (NMT), an architecture tailored for decoding compound tokens autoregressively, similar to processing flattened tokens, but with low memory usage. The NMT consists of two transformers: the main decoder that models a sequence of compound tokens and the sub-decoder for modeling sub-tokens of each compound token. The experiment results showed that applying the NMT to compound tokens can enhance the performance in terms of better perplexity in processing various symbolic music datasets and discrete audio tokens from the MAESTRO dataset.

Daewoong Kim, Hao-Wen Dong, Dasaem Jeong

Modeling the natural contour of fundamental frequency (F0) plays a critical role in music audio synthesis. However, transcribing and managing multiple F0 contours in polyphonic music is challenging, and explicit F0 contour modeling has not yet been explored for polyphonic instrumental synthesis. In this paper, we present ViolinDiff, a two-stage diffusion-based synthesis framework. For a given violin MIDI file, the first stage estimates the F0 contour as pitch bend information, and the second stage generates mel spectrogram incorporating these expressive details. The quantitative metrics and listening test results show that the proposed model generates more realistic violin sounds than the model without explicit pitch bend modeling. Audio samples are available online: daewoung.github.io/ViolinDiff-Demo.

Huan Zhang, Taegyun Kwon, Anders Friburg et al.

This paper presents a comprehensive documentation of RenCon 2025, the revival of the expressive performance rendering competition which took place at ISMIR 2025 in Daejeon, Korea. The competition attracted 9 entries from international research groups, representing diverse approaches to expressive piano performance rendering. The two-phase assessment structure comprised a preliminary online evaluation and live real-time rendering at the conference. We analyze the competition format, participant demographics, system performance, and lessons learned for future iterations. The results demonstrate significant advances in expressive rendering capabilities while highlighting remaining challenges in achieving human-level musical expression.

Taegyun Kwon, Dasaem Jeong, Juhan Nam

In recent years, advancements in neural network designs and the availability of large-scale labeled datasets have led to significant improvements in the accuracy of piano transcription models. However, most previous work focused on high-performance offline transcription, neglecting deliberate consideration of model size. The goal of this work is to implement real-time inference for piano transcription while ensuring both high performance and lightweight. To this end, we propose novel architectures for convolutional recurrent neural networks, redesigning an existing autoregressive piano transcription model. First, we extend the acoustic module by adding a frequency-conditioned FiLM layer to the CNN module to adapt the convolutional filters on the frequency axis. Second, we improve note-state sequence modeling by using a pitchwise LSTM that focuses on note-state transitions within a note. In addition, we augment the autoregressive connection with an enhanced recursive context. Using these components, we propose two types of models; one for high performance and the other for high compactness. Through extensive experiments, we show that the proposed models are comparable to state-of-the-art models in terms of note accuracy on the MAESTRO dataset. We also investigate the effective model size and real-time inference latency by gradually streamlining the architecture. Finally, we conduct cross-data evaluation on unseen piano datasets and in-depth analysis to elucidate the effect of the proposed components in the view of note length and pitch range.

Jongmin Jung, Andreas Jansson, Dasaem Jeong

MusicGen is a music generation language model (LM) that can be conditioned on textual descriptions and melodic features. We introduce MusicGen-Chord, which extends this capability by incorporating chord progression features. This model modifies one-hot encoded melody chroma vectors into multi-hot encoded chord chroma vectors, enabling the generation of music that reflects both chord progressions and textual descriptions. Furthermore, we developed MusicGen-Remixer, an application utilizing MusicGen-Chord to generate remixes of input music conditioned on textual descriptions. Both models are integrated into Replicate's web-UI using cog, facilitating broad accessibility and user-friendly controllable interaction for creating and experiencing AI-generated music.

Eunjin Choi, Hyerin Kim, Jiwoo Ryu et al.

A large-scale dataset is essential for training a well-generalized deep-learning model. Most such datasets are collected via scraping from various internet sources, inevitably introducing duplicated data. In the symbolic music domain, these duplicates often come from multiple user arrangements and metadata changes after simple editing. However, despite critical issues such as unreliable training evaluation from data leakage during random splitting, dataset duplication has not been extensively addressed in the MIR community. This study investigates the dataset duplication issues regarding Lakh MIDI Dataset (LMD), one of the largest publicly available sources in the symbolic music domain. To find and evaluate the best retrieval method for duplicated data, we employed the Clean MIDI subset of the LMD as a benchmark test set, in which different versions of the same songs are grouped together. We first evaluated rule-based approaches and previous symbolic music retrieval models for de-duplication and also investigated with a contrastive learning-based BERT model with various augmentations to find duplicate files. As a result, we propose three different versions of the filtered list of LMD, which filters out at least 38,134 samples in the most conservative settings among 178,561 files.

Jongmin Jung, Dongmin Kim, Sihun Lee et al.

Music exists in various modalities, such as score images, symbolic scores, MIDI, and audio. Translations between each modality are established as core tasks of music information retrieval, such as automatic music transcription (audio-to-MIDI) and optical music recognition (score image to symbolic score). However, most past work on multimodal translation trains specialized models on individual translation tasks. In this paper, we propose a unified approach, where we train a general-purpose model on many translation tasks simultaneously. Two key factors make this unified approach viable: a new large-scale dataset and the tokenization of each modality. Firstly, we propose a new dataset that consists of more than 1,300 hours of paired audio-score image data collected from YouTube videos, which is an order of magnitude larger than any existing music modal translation datasets. Secondly, our unified tokenization framework discretizes score images, audio, MIDI, and MusicXML into a sequence of tokens, enabling a single encoder-decoder Transformer to tackle multiple cross-modal translation as one coherent sequence-to-sequence task. Experimental results confirm that our unified multitask model improves upon single-task baselines in several key areas, notably reducing the symbol error rate for optical music recognition from 24.58% to a state-of-the-art 13.67%, while similarly substantial improvements are observed across the other translation tasks. Notably, our approach achieves the first successful score-image-conditioned audio generation, marking a significant breakthrough in cross-modal music generation.

Jongmin Jung, Dasaem Jeong

This paper introduces LAV (Latent Audio-Visual), a system that integrates EnCodec's neural audio compression with StyleGAN2's generative capabilities to produce visually dynamic outputs driven by pre-recorded audio. Unlike previous works that rely on explicit feature mappings, LAV uses EnCodec embeddings as latent representations, directly transformed into StyleGAN2's style latent space via randomly initialized linear mapping. This approach preserves semantic richness in the transformation, enabling nuanced and semantically coherent audio-visual translations. The framework demonstrates the potential of using pretrained audio compression models for artistic and computational applications.

Sihun Lee, Dasaem Jeong

Leitmotifs are musical phrases that are reprised in various forms throughout a piece. Due to diverse variations and instrumentation, detecting the occurrence of leitmotifs from audio recordings is a highly challenging task. Leitmotif detection may be handled as a subcategory of audio event detection, where leitmotif activity is predicted at the frame level. However, as leitmotifs embody distinct, coherent musical structures, a more holistic approach akin to bounding box regression in visual object detection can be helpful. This method captures the entirety of a motif rather than fragmenting it into individual frames, thereby preserving its musical integrity and producing more useful predictions. We present our experimental results on tackling leitmotif detection as a boundary regression task.

Dasaem Jeong, Seungheon Doh, Taegyun Kwon

The goal of this paper to generate a visually appealing video that responds to music with a neural network so that each frame of the video reflects the musical characteristics of the corresponding audio clip. To achieve the goal, we propose a neural music visualizer directly mapping deep music embeddings to style embeddings of StyleGAN, named TräumerAI, which consists of a music auto-tagging model using short-chunk CNN and StyleGAN2 pre-trained on WikiArt dataset. Rather than establishing an objective metric between musical and visual semantics, we manually labeled the pairs in a subjective manner. An annotator listened to 100 music clips of 10 seconds long and selected an image that suits the music among the 200 StyleGAN-generated examples. Based on the collected data, we trained a simple transfer function that converts an audio embedding to a style embedding. The generated examples show that the mapping between audio and video makes a certain level of intra-segment similarity and inter-segment dissimilarity.

Taegyun Kwon, Dasaem Jeong, Juhan Nam

Recent advances in polyphonic piano transcription have been made primarily by a deliberate design of neural network architectures that detect different note states such as onset or sustain and model the temporal evolution of the states. The majority of them, however, use separate neural networks for each note state, thereby optimizing multiple loss functions, and also they handle the temporal evolution of note states by abstract connections between the state-wise neural networks or using a post-processing module. In this paper, we propose a unified neural network architecture where multiple note states are predicted as a softmax output with a single loss function and the temporal order is learned by an auto-regressive connection within the single neural network. This compact model allows to increase note states without architectural complexity. Using the MAESTRO dataset, we examine various combinations of multiple note states including on, onset, sustain, re-onset, offset, and off. We also show that the autoregressive module effectively learns inter-state dependency of notes. Finally, we show that our proposed model achieves performance comparable to state-of-the-arts with fewer parameters.

Taegyun Kwon, Dasaem Jeong, Juhan Nam

We propose a framework for audio-to-score alignment on piano performance that employs automatic music transcription (AMT) using neural networks. Even though the AMT result may contain some errors, the note prediction output can be regarded as a learned feature representation that is directly comparable to MIDI note or chroma representation. To this end, we employ two recurrent neural networks that work as the AMT-based feature extractors to the alignment algorithm. One predicts the presence of 88 notes or 12 chroma in frame-level and the other detects note onsets in 12 chroma. We combine the two types of learned features for the audio-to-score alignment. For comparability, we apply dynamic time warping as an alignment algorithm without any additional post-processing. We evaluate the proposed framework on the MAPS dataset and compare it to previous work. The result shows that the alignment framework with the learned features significantly improves the accuracy, achieving less than 10 ms in mean onset error.