The annotation of music content is a complex process to represent due to its inherent multifaceted, subjectivity, and interdisciplinary nature. Numerous systems and conventions for annotating music have been developed as independent standards over the past decades. Little has been done to make them interoperable, which jeopardises cross-corpora studies as it requires users to familiarise with a multitude of conventions. Most of these systems lack the semantic expressiveness needed to represent the complexity of the musical language and cannot model multi-modal annotations originating from audio and symbolic sources. In this article, we introduce the Music Annotation Pattern, an Ontology Design Pattern (ODP) to homogenise different annotation systems and to represent several types of musical objects (e.g. chords, patterns, structures). This ODP preserves the semantics of the object's content at different levels and temporal granularity. Moreover, our ODP accounts for multi-modality upfront, to describe annotations derived from different sources, and it is the first to enable the integration of music datasets at a large scale.
Pre-trained language models have achieved impressive results in various music understanding and generation tasks. However, existing pre-training methods for symbolic melody generation struggle to capture multi-scale, multi-dimensional structural information in note sequences, due to the domain knowledge discrepancy between text and music. Moreover, the lack of available large-scale symbolic melody datasets limits the pre-training improvement. In this paper, we propose MelodyGLM, a multi-task pre-training framework for generating melodies with long-term structure. We design the melodic n-gram and long span sampling strategies to create local and global blank infilling tasks for modeling the local and global structures in melodies. Specifically, we incorporate pitch n-grams, rhythm n-grams, and their combined n-grams into the melodic n-gram blank infilling tasks for modeling the multi-dimensional structures in melodies. To this end, we have constructed a large-scale symbolic melody dataset, MelodyNet, containing more than 0.4 million melody pieces. MelodyNet is utilized for large-scale pre-training and domain-specific n-gram lexicon construction. Both subjective and objective evaluations demonstrate that MelodyGLM surpasses the standard and previous pre-training methods. In particular, subjective evaluations show that, on the melody continuation task, MelodyGLM gains average improvements of 0.82, 0.87, 0.78, and 0.94 in consistency, rhythmicity, structure, and overall quality, respectively. Notably, MelodyGLM nearly matches the quality of human-composed melodies on the melody inpainting task.
Symbolic music generation aims to create musical notes, which can help users compose music, such as generating target instrumental tracks from scratch, or based on user-provided source tracks. Considering the diverse and flexible combination between source and target tracks, a unified model capable of generating any arbitrary tracks is of crucial necessity. Previous works fail to address this need due to inherent constraints in music representations and model architectures. To address this need, we propose a unified representation and diffusion framework named GETMusic (`GET' stands for GEnerate music Tracks), which includes a novel music representation named GETScore, and a diffusion model named GETDiff. GETScore represents notes as tokens and organizes them in a 2D structure, with tracks stacked vertically and progressing horizontally over time. During training, tracks are randomly selected as either the target or source. In the forward process, target tracks are corrupted by masking their tokens, while source tracks remain as ground truth. In the denoising process, GETDiff learns to predict the masked target tokens, conditioning on the source tracks. With separate tracks in GETScore and the non-autoregressive behavior of the model, GETMusic can explicitly control the generation of any target tracks from scratch or conditioning on source tracks. We conduct experiments on music generation involving six instrumental tracks, resulting in a total of 665 combinations. GETMusic provides high-quality results across diverse combinations and surpasses prior works proposed for some specific combinations.
In this paper we propose the Music Note Ontology, an ontology for modelling music notes and their realisation. The ontology addresses the relation between a note represented in a symbolic representation system, and its realisation, i.e. a musical performance. This work therefore aims to solve the modelling and representation issues that arise when analysing the relationships between abstract symbolic features and the corresponding physical features of an audio signal. The ontology is composed of three different Ontology Design Patterns (ODP), which model the structure of the score (Score Part Pattern), the note in the symbolic notation (Music Note Pattern) and its realisation (Musical Object Pattern).
In this report, we present our award-winning solutions for the Music Demixing Track of Sound Demixing Challenge 2023. We focus on two methods designed for this challenge: a time-efficient source separation network that achieves state-of-the-art results on the MUSDB benchmark and a loss masking method for noise-robust source separation. Code for reproducing model training and final submissions is available at github.com/kuielab/sdx23.
Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering mislabeled individual instrument tracks becomes a significant challenge to address. This paper introduces an automated technique for refining the labels in a partially mislabeled dataset. Our proposed self-refining technique, employed with a noisy-labeled dataset, results in only a 1% accuracy degradation in multi-label instrument recognition compared to a classifier trained on a clean-labeled dataset. The study demonstrates the importance of refining noisy-labeled data in MSS model training and shows that utilizing the refined dataset leads to comparable results derived from a clean-labeled dataset. Notably, upon only access to a noisy dataset, MSS models trained on a self-refined dataset even outperform those trained on a dataset refined with a classifier trained on clean labels.
Terahertz (THz) band is currently envisioned as the key building block to achieving the future sixth generation (6G) wireless systems. The ultra-wide bandwidth and very narrow beamwidth of THz systems offer the next order of magnitude in user densities and multi-functional behavior. However, wide bandwidth results in a frequency-dependent beampattern causing the beams generated at different subcarriers split and point to different directions. Furthermore, mutual coupling degrades the system's performance. This paper studies the compensation of both beam-split and mutual coupling for direction-of-arrival (DoA) estimation by modeling the beam-split and mutual coupling as an array imperfection. We propose a subspace-based approach using multiple signal classification with CalibRated for bEAam-split and Mutual coupling (CREAM-MUSIC) algorithm for this purpose. Via numerical simulations, we show the proposed CREAM-MUSIC approach accurately estimates the DoAs in the presence of beam-split and mutual coupling.
Digital storytelling, as an art form, has struggled with cost-quality balance. The emergence of AI-generated Content (AIGC) is considered as a potential solution for efficient digital storytelling production. However, the specific form, effects, and impacts of this fusion remain unclear, leaving the boundaries of AIGC combined with storytelling undefined. This work explores the current integration state of AIGC and digital storytelling, investigates the artistic value of their fusion in a sample project, and addresses common issues through interviews. Through our study, we conclude that AIGC, while proficient in image creation, voiceover production, and music composition, falls short of replacing humans due to the irreplaceable elements of human creativity and aesthetic sensibilities at present, especially in complex character animations, facial expressions, and sound effects. The research objective is to increase public awareness of the current state, limitations, and challenges arising from combining AIGC and digital storytelling.
Visuals are a core part of our experience of music, owing to the way they can amplify the emotions and messages conveyed through the music. However, creating music visualization is a complex, time-consuming, and resource-intensive process. We introduce Generative Disco, a generative AI system that helps generate music visualizations with large language models and text-to-image models. Users select intervals of music to visualize and then parameterize that visualization by defining start and end prompts. These prompts are warped between and generated according to the beat of the music for audioreactive video. We introduce design patterns for improving generated videos: "transitions", which express shifts in color, time, subject, or style, and "holds", which encourage visual emphasis and consistency. A study with professionals showed that the system was enjoyable, easy to explore, and highly expressive. We conclude on use cases of Generative Disco for professionals and how AI-generated content is changing the landscape of creative work.
Dancing with music is always an essential human art form to express emotion. Due to the high temporal-spacial complexity, long-term 3D realist dance generation synchronized with music is challenging. Existing methods suffer from the freezing problem when generating long-term dances due to error accumulation and training-inference discrepancy. To address this, we design a conditional diffusion model, LongDanceDiff, for this sequence-to-sequence long-term dance generation, addressing the challenges of temporal coherency and spatial constraint. LongDanceDiff contains a transformer-based diffusion model, where the input is a concatenation of music, past motions, and noised future motions. This partial noising strategy leverages the full-attention mechanism and learns the dependencies among music and past motions. To enhance the diversity of generated dance motions and mitigate the freezing problem, we introduce a mutual information minimization objective that regularizes the dependency between past and future motions. We also address common visual quality issues in dance generation, such as foot sliding and unsmooth motion, by incorporating spatial constraints through a Global-Trajectory Modulation (GTM) layer and motion perceptual losses, thereby improving the smoothness and naturalness of motion generation. Extensive experiments demonstrate a significant improvement in our approach over the existing state-of-the-art methods. We plan to release our codes and models soon.