相关论文: Do we need more complex representations for struct…

Deep learning algorithms are increasingly developed for learning to compose music in the form of MIDI files. However, whether such algorithms work well for composing guitar tabs, which are quite different from MIDIs, remain relatively…

Automatic Music Transcription has seen significant progress in recent years by training custom deep neural networks on large datasets. However, these models have required extensive domain-specific design of network architectures,…

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens…

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…

Polyphonic music generation is still a challenge direction due to its correct between generating melody and harmony. Most of the previous studies used RNN-based models. However, the RNN-based models are hard to establish the relationship…

Supervised music representation learning has been performed mainly using semantic labels such as music genres. However, annotating music with semantic labels requires time and cost. In this work, we investigate the use of factual metadata…

Symbolic Music Generation relies on the contextual representation capabilities of the generative model, where the most prevalent approach is the Transformer-based model. The learning of musical context is also related to the structural…

There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which…

Automatic music transcription (AMT) has achieved remarkable progress for instruments such as the piano, largely due to the availability of large-scale, high-quality datasets. In contrast, violin AMT remains underexplored due to limited…

For the tasks of automatic music emotion recognition, genre recognition, music recommendation it is helpful to be able to extract mode from any section of a musical piece as a perceived amount of major or minor mode (majorness) inside that…

Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep…

Recent music generation methods based on transformers have a context window of up to a minute. The music generated by these methods is largely unstructured beyond the context window. With a longer context window, learning long-scale…

Music is a structured and perceptually rich sequence of sounds in time, whose perception is shaped by the interplay of expectation and uncertainty about what comes next. Yet the uncertainty we infer from music depends on how the musical…

Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit…

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…

We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer…

Existing methods for expressive music performance rendering rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and…

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Music annotation has always been one of the critical topics in the field of Music Information Retrieval (MIR). Traditional models use supervised learning for music annotation tasks. However, as supervised machine learning approaches…

This paper proposes a novel Transformer-based model for music score infilling, to generate a music passage that fills in the gap between given past and future contexts. While existing infilling approaches can generate a passage that…