相关论文: Instrument Separation of Symbolic Music by Explici…

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its…

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the…

In recent years, text-to-audio systems have achieved remarkable success, enabling the generation of complete audio segments directly from text descriptions. While these systems also facilitate music creation, the element of human creativity…

Symbolic music analysis tasks are often performed by models originally developed for Natural Language Processing, such as Transformers. Such models require the input data to be represented as sequences, which is achieved through a process…

We propose a visually conditioned music remixing system by incorporating deep visual and audio models. The method is based on a state of the art audio-visual source separation model which performs music instrument source separation with…

Music creation involves not only composing the different parts (e.g., melody, chords) of a musical work but also arranging/selecting the instruments to play the different parts. While the former has received increasing attention, the latter…

Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance requires a large amount of image-annotation pairs for training and is…

In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores. Thus far, sequence models have yielded fruitful results with note-level (MIDI-equivalent)…

Since most of music has repetitive structures from motifs to phrases, repeating musical ideas can be a basic operation for music composition. The basic block that we focus on is conceptualized as loops which are essential ingredients of…

Audio inpainting seeks to restore missing segments in degraded recordings. Previous diffusion-based methods exhibit impaired performance when the missing region is large. We introduce the first approach that applies discrete diffusion over…

Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by…

In this paper we introduce multi-label ferns, and apply this technique for automatic classification of musical instruments in audio recordings. We compare the performance of our proposed method to a set of binary random ferns, using jazz…

The ''pretraining-and-finetuning'' paradigm has become a norm for training domain-specific models in natural language processing and computer vision. In this work, we aim to examine this paradigm for symbolic music generation through…

With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem. While existing deep learning models implicitly absorb the spatial…

In this paper, we consider the problem of probabilistically modelling symbolic music data. We introduce a representation which reduces polyphonic music to a univariate categorical sequence. In this way, we are able to apply state of the art…

The field of Automatic Music Generation has seen significant progress thanks to the advent of Deep Learning. However, most of these results have been produced by unconditional models, which lack the ability to interact with their users, not…

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs. These random mixes have mismatched characteristics compared to real…

Music Visualization is basically the transformation of data from the aural to the visual space. There are a variety of music visualizations, across applications, present on the web. Models of Visualization include conceptual frameworks…

Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for mixing style transfer are limited in that they often…

Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures…