Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a mixture to extract the target sources, the flexibility and generalization capabilities of generative diffusion models are giving rise to a novel class of solutions for this complicated task. In this work, we explore singing voice separation from real music recordings using a diffusion model which is trained to generate the solo vocals conditioned on the corresponding mixture. Our approach improves upon prior generative systems and achieves competitive objective scores against non-generative baselines when trained with supplementary data. The iterative nature of diffusion sampling enables the user to control the quality-efficiency trade-off, and also refine the output when needed. We present an ablation study of the sampling algorithm, highlighting the effects of the user-configurable parameters.

Current methods for Music Structure Analysis (MSA) focus primarily on audio data. While symbolic music can be synthesized into audio and analyzed using existing MSA techniques, such an approach does not exploit symbolic music's rich explicit representation of pitch, timing, and instrumentation. A key subproblem of MSA is section boundary detection-determining whether a given point in time marks the transition between musical sections. In this paper, we study automatic section boundary detection for symbolic music. First, we introduce a human-annotated MIDI dataset for section boundary detection, consisting of metadata from 6134 MIDI files that we manually curated from the Lakh MIDI dataset. Second, we train a deep learning model to classify the presence of section boundaries within a fixed-length musical window. Our data representation involves a novel encoding scheme based on synthesized overtones to encode arbitrary MIDI instrumentations into 3-channel piano rolls. Our model achieves an F1 score of 0.77, improving over the analogous audio-based supervised learning approach and the unsupervised block-matching segmentation (CBM) audio approach by 0.22 and 0.31, respectively. We release our dataset, code, and models.

We introduce a novel technique for creative audio resynthesis that operates by reworking the concept of granular synthesis at the latent vector level. Our approach creates a "granular codebook" by encoding a source audio corpus into latent vector segments, then matches each latent grain of a target audio signal to its closest counterpart in the codebook. The resulting hybrid sequence is decoded to produce audio that preserves the target's temporal structure while adopting the source's timbral characteristics. This technique requires no model training, works with diverse audio materials, and naturally avoids the discontinuities typical of traditional concatenative synthesis through the codec's implicit interpolation during decoding. We include supplementary material at https://github.com/naotokui/latentgranular/ , as well as a proof-of-concept implementation to allow users to experiment with their own sounds at https://huggingface.co/spaces/naotokui/latentgranular .

Automatic sample identification (ASID), the detection and identification of portions of audio recordings that have been reused in new musical works, is an essential but challenging task in the field of audio query-based retrieval. While a related task, audio fingerprinting, has made significant progress in accurately retrieving musical content under "real world" (noisy, reverberant) conditions, ASID systems struggle to identify samples that have undergone musical modifications. Thus, a system robust to common music production transformations such as time-stretching, pitch-shifting, effects processing, and underlying or overlaying music is an important open challenge. In this work, we propose a lightweight and scalable encoding architecture employing a Graph Neural Network within a contrastive learning framework. Our model uses only 9% of the trainable parameters compared to the current state-of-the-art system while achieving comparable performance, reaching a mean average precision (mAP) of 44.2%. To enhance retrieval quality, we introduce a two-stage approach consisting of an initial coarse similarity search for candidate selection, followed by a cross-attention classifier that rejects irrelevant matches and refines the ranking of retrieved candidates - an essential capability absent in prior models. In addition, because queries in real-world applications are often short in duration, we benchmark our system for short queries using new fine-grained annotations for the Sample100 dataset, which we publish as part of this work.

Text-to-audio diffusion models produce high-quality and diverse music but many, if not most, of the SOTA models lack the fine-grained, time-varying controls essential for music production. ControlNet enables attaching external controls to a pre-trained generative model by cloning and fine-tuning its encoder on new conditionings. However, this approach incurs a large memory footprint and restricts users to a fixed set of controls. We propose a lightweight, modular architecture that considerably reduces parameter count while matching ControlNet in audio quality and condition adherence. Our method offers greater flexibility and significantly lower memory usage, enabling more efficient training and deployment of independent controls. We conduct extensive objective and subjective evaluations and provide numerous audio examples on the accompanying website at https://lightlatentcontrol.github.io

Symbolic music research plays a crucial role in musicrelated machine learning, but MIDI data can be complex 2. SOFTWARE OVERVIEW for those without musical expertise. To address this issue, 2.1 Key functionality we present MidiTok Visualizer, a web application designed to facilitate the exploration and visualization of various MidiTok Visualizer is a web application designed for visualizing MIDI tokenization methods from the MidiTok Python and analyzing MIDI file tokenization techniques package. MidiTok Visualizer offers numerous customizable from the MidiTok Python package. The key capabilities parameters, enabling users to upload MIDI files to visualize of the tool are as follows: tokenized data alongside an interactive piano roll. Allows users to upload a MIDI file and view a graphical representation of the tokens generated by 1. INTRODUCTION

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.

Generative AI models have recently blossomed, significantly impacting artistic and musical traditions. Research investigating how humans interact with and deem these models is therefore crucial. Through a listening and reflection study, we explore participants' perspectives on AI- vs human-generated progressive metal, in symbolic format, using rock music as a control group. AI-generated examples were produced by ProgGP, a Transformer-based model. We propose a mixed methods approach to assess the effects of generation type (human vs. AI), genre (progressive metal vs. rock), and curation process (random vs. cherry-picked). This combines quantitative feedback on genre congruence, preference, creativity, consistency, playability, humanness, and repeatability, and qualitative feedback to provide insights into listeners' experiences. A total of 32 progressive metal fans completed the study. Our findings validate the use of fine-tuning to achieve genre-specific specialization in AI music generation, as listeners could distinguish between AI-generated rock and progressive metal. Despite some AI-generated excerpts receiving similar ratings to human music, listeners exhibited a preference for human compositions. Thematic analysis identified key features for genre and AI vs. human distinctions. Finally, we consider the ethical implications of our work in promoting musical data diversity within MIR research by focusing on an under-explored genre.

We introduce Composer's Assistant 2, a system for interactive human-computer composition in the REAPER digital audio workstation. Our work upgrades the Composer's Assistant system (which performs multi-track infilling of symbolic music at the track-measure level) with a wide range of new controls to give users fine-grained control over the system's outputs. Controls introduced in this work include two types of rhythmic conditioning controls, horizontal and vertical note onset density controls, several types of pitch controls, and a rhythmic interest control. We train a T5-like transformer model to implement these controls and to serve as the backbone of our system. With these controls, we achieve a dramatic improvement in objective metrics over the original system. We also study how well our model understands the meaning of our controls, and we conduct a listening study that does not find a significant difference between real music and music composed in a co-creative fashion with our system. We release our complete system, consisting of source code, pretrained models, and REAPER scripts.

This article presents a benchmark study of symbolic piano music classification using the masked language modelling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, we consider two types of MIDI data: MIDI scores, which are musical scores rendered directly into MIDI with no dynamics and precisely aligned with the metrical grid notated by its composer and MIDI performances, which are MIDI encodings of human performances of musical scoresheets. With five public-domain datasets of single-track piano MIDI files, we pre-train two 12-layer Transformer models using the BERT approach, one for MIDI scores and the other for MIDI performances, and fine-tune them for four downstream classification tasks. These include two note-level classification tasks (melody extraction and velocity prediction) and two sequence-level classification tasks (style classification and emotion classification). Our evaluation shows that the BERT approach leads to higher classification accuracy than recurrent neural network (RNN)-based baselines.