相关论文: Nested Music Transformer: Sequentially Decoding Co…

The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of…

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity. Despite very promising progress on image and short sequence generation, symbolic music…

Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage…

In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the…

As digital music production has become mainstream, the selection of appropriate virtual instruments plays a crucial role in determining the quality of music. To search the musical instrument samples or virtual instruments that make one's…

We present a polynomial-time algorithm that discovers all maximal patterns in a point set, $D\subset\mathbb{R}^k$, that are related by transformations in a user-specified class, $F$, of bijections over $\mathbb{R}^k$. We also present a…

Several adaptations of Transformers models have been developed in various domains since its breakthrough in Natural Language Processing (NLP). This trend has spread into the field of Music Information Retrieval (MIR), including studies…

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

Representation learning focused on disentangling the underlying factors of variation in given data has become an important area of research in machine learning. However, most of the studies in this area have relied on datasets from the…

Transformer architectures offer significant advantages regarding the generation of symbolic music; their capabilities for incorporating user preferences toward what they generate is being studied under many aspects. This paper studies the…

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…

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly…

Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or…

This paper presents enhancements to the MT3 model, a state-of-the-art (SOTA) token-based multi-instrument automatic music transcription (AMT) model. Despite SOTA performance, MT3 has the issue of instrument leakage, where transcriptions are…

Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic manner. To tackle this…

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright…

We propose a transformer-based rhythm quantization model that incorporates beat and downbeat information to quantize MIDI performances into metrically-aligned, human-readable scores. We propose a beat-based preprocessing method that…

Conditional music generation offers significant advantages in terms of user convenience and control, presenting great potential in AI-generated content research. However, building conditional generative systems for multitrack popular songs…