相关论文: Time-Shifted Token Scheduling for Symbolic Music G…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

A key aspect of machine learning models lies in their ability to learn efficient intermediate features. However, the input representation plays a crucial role in this process, and polyphonic musical scores remain a particularly complex type…

Emotion-driven melody harmonization aims to generate diverse harmonies for a single melody to convey desired emotions. Previous research found it hard to alter the perceived emotional valence of lead sheets only by harmonizing the same…

Composing coherent long-form music remains a significant challenge due to the complexity of modeling long-range dependencies and the prohibitive memory and computational requirements associated with lengthy audio representations. In this…

Discrete representation learning has shown promising results across various domains, including generation and understanding in image, speech and language. Inspired by these advances, we propose MuseTok, a tokenization method for symbolic…

Generating music with deep neural networks has been an area of active research in recent years. While the quality of generated samples has been steadily increasing, most methods are only able to exert minimal control over the generated…

A method is proposed which enables one to produce musical compositions by using transposition in place of harmonic progression. A transposition scale is introduced to provide a set of intervals commensurate with the musical scale, such as…

Symbolic music representation is a fundamental challenge in computational musicology. While grid-based representations effectively preserve pitch-time spatial correspondence, their inherent data sparsity leads to low encoding efficiency.…

Current state-of-the-art AI based classical music creation algorithms such as Music Transformer are trained by employing single sequence of notes with time-shifts. The major drawback of absolute time interval expression is the difficulty of…

Symbolic music segmentation is the process of dividing symbolic melodies into smaller meaningful groups, such as melodic phrases. We proposed an unsupervised method for segmenting symbolic music. The proposed model is based on an ensemble…

Sequence modeling with neural networks has lead to powerful models of symbolic music data. We address the problem of exploiting these models to reach creative musical goals, by combining with human input. To this end we generalise previous…

Having large batch sizes is one of the most critical aspects of increasing the accelerator efficiency and the performance of DNN model inference. However, existing model serving systems cannot achieve adequate batch sizes while meeting…

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…

Existing work in automatic music generation has mostly focused on end-to-end systems that generate either entire compositions or continuations of pieces, which are difficult for composers to iterate on. The area of computer-assisted…

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…

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…

As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to generate a single…

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that…

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing…

Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we…