相关论文: Exploring Tokenization Methods for Multitrack Shee…

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Music mixing is compositional -- experts combine multiple audio processors to achieve a cohesive mix from dry source tracks. We propose a method to reverse engineer this process from the input and output audio. First, we create a mixing…

In this paper, we formalize practical byte pair encoding tokenization as it is used in large language models and other NLP systems, in particular we formally define and investigate the semantics of the SentencePiece and HuggingFace…

The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we…

Graphs can be leveraged to model polyphonic multitrack symbolic music, where notes, chords and entire sections may be linked at different levels of the musical hierarchy by tonal and rhythmic relationships. Nonetheless, there is a lack of…

We consider the problem of computing the capacity of a coded, multicast network over a small alphabet. We introduce a novel approach to this problem based on mixed integer programming. As an application of our approach, we recover, extend…

Multi-label classification poses challenges due to imbalanced and noisy labels in training data. We propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced…

The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph…

Stochastic computing (SC) is a high density, low-power computation technique which encodes values as unary bitstreams instead of binary-encoded (BE) values. Practical SC implementations require deterministic or pseudo-random number…

Byte-Pair Encoding (BPE) is a widely used method for subword tokenization, with origins in grammar-based text compression. It is employed in a variety of language processing tasks such as machine translation or large language model (LLM)…

The relationship between tokenizer algorithm (e.g., Byte-Pair Encoding (BPE), Unigram), morphological alignment, tokenization quality (e.g., compression efficiency), and downstream performance remains largely unclear, particularly for…

We propose a novel symbolic music representation and Generative Adversarial Network (GAN) framework specially designed for symbolic multitrack music generation. The main theme of symbolic music generation primarily encompasses the…

Linear nested codes, where two or more sub-codes are nested in a global code, have been proposed as candidates for reliable multi-terminal communication. In this paper, we consider nested array-based spatially coupled low-density…

We propose different methods for alternative representation and visual augmentation of sheet music that help users gain an overview of general structure, repeating patterns, and the similarity of segments. To this end, we explored mapping…

In this demo we show a novel approach to score following. Instead of relying on some symbolic representation, we are using a multi-modal convolutional neural network to match the incoming audio stream directly to sheet music images. This…

In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting. Motivated by recent advances in the computer vision domain, we are the first to explore the combination of pre-trained text-to-audio…

Music rearrangement is a common music practice of reconstructing and reconceptualizing a piece using new composition or instrumentation styles, which is also an important task of automatic music generation. Existing studies typically model…

This paper introduces a simple method for producing multichannel MIDI music that is based on randomness and simple probabilities. One distinctive feature of the method is that it produces and sends in parallel to the sound card more than…

A representation technique that allows encoding music in a way that contains musical meaning would improve the results of any model trained for computer music tasks like generation of melodies and harmonies of better quality. The field of…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…