相关论文: Generating High-quality Symbolic Music Using Fine-…

Recent advances in generative models and adversarial training have enabled artificially generating artworks in various artistic styles. It is highly desirable to gain more control over the generated style in practice. However, artistic…

Loopable music generation systems enable diverse applications, but they often lack controllability and customization capabilities. We argue that enhancing controllability can enrich these models, with emotional expression being a crucial…

Music generation schemes using language modeling rely on a vocabulary of audio tokens, generally provided as codes in a discrete latent space learnt by an auto-encoder. Multi-stage quantizers are often employed to produce these tokens,…

In this paper, we propose a multi-stage and high-resolution model for image synthesis that uses fine-grained attributes and masks as input. With a fine-grained attribute, the proposed model can detailedly constrain the features of the…

Modern embedding-based metrics for evaluation of generated text generally fall into one of two paradigms: discriminative metrics that are trained to directly predict which outputs are of higher quality according to supervised human…

Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio. However, due to their Langevin-inspired sampling mechanisms, their…

In many musical traditions, the melody line is of primary significance in a piece. Human listeners can readily distinguish melodies from accompaniment; however, making this distinction given only the written score -- i.e. without listening…

Pattern discovery algorithms in the music domain aim to find meaningful components in musical compositions. Over the years, although many algorithms have been developed for pattern discovery in music data, it remains a challenging task. To…

While deep generative models have empowered music generation, it remains a challenging and under-explored problem to edit an existing musical piece at fine granularity. In this paper, we propose SDMuse, a unified Stochastic Differential…

Blind music source separation has been a popular and active subject of research in both the music information retrieval and signal processing communities. To counter the lack of available multi-track data for supervised model training, a…

Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces. In general, an analogy is made by partially transferring the music abstractions, i.e., high-level representations and their…

Music source separation (MSS) aims to extract individual instrument sources from their mixture. While most existing methods focus on the widely adopted four-stem separation setup (vocals, bass, drums, and other instruments), this approach…

Melody harmonization has long been closely associated with chorales composed by Johann Sebastian Bach. Previous works rarely emphasised chorale generation conditioned on chord progressions, and there has been a lack of focus on assistive…

In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated. This leads to…

Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced…

Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source and the target sequences. We present a method to explicitly…

We propose MelodySim, a melody-aware music similarity model and dataset for plagiarism detection. First, we introduce a novel method to construct a dataset focused on melodic similarity. By augmenting Slakh2100, an existing MIDI dataset, we…

The aim of this study is to teach an algorithm how to recognize different types of music. Users will submit songs for analysis. Since the algorithm hasn't heard these songs before, it needs to figure out what makes each song unique. It does…

We introduce a novel resampling criterion using lift scores, for improving compositional generation in diffusion models. By leveraging the lift scores, we evaluate whether generated samples align with each single condition and then compose…

Lyric-to-melody generation, which generates melody according to given lyrics, is one of the most important automatic music composition tasks. With the rapid development of deep learning, previous works address this task with end-to-end…