相关论文: MuCPT: Music-related Natural Language Model Contin…

In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible…

Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance,…

Music captioning, or the task of generating a natural language description of music, is useful for both music understanding and controllable music generation. Training captioning models, however, typically requires high-quality music…

Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its…

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

The rise of music large language models (LLMs) demands robust methods of evaluating output quality, especially in distinguishing high-quality compositions from "garbage music". Curiously, we observe that the standard cross-entropy loss -- a…

Benefiting from large-scale datasets and pre-trained models, the field of generative models has recently gained significant momentum. However, most datasets for symbolic music are very small, which potentially limits the performance of…

The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…

Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. Continual pre-training (CPT) enhances LLM capabilities by imbuing new domain-specific or…

Recent years have witnessed a rapid growth of large-scale language models in the domain of music audio. Such models enable end-to-end generation of higher-quality music, and some allow conditioned generation using text descriptions.…

Automatic music generation with artificial intelligence typically requires a large amount of data which is hard to obtain for many less common genres and musical instruments. To tackle this issue, we present ongoing work and preliminary…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, with pre-training stage serving as the cornerstone of their capabilities. However, the conventional fixed-length data composition strategy for…

Mathematical reasoning is a cornerstone of human intelligence and a key benchmark for advanced capabilities in large language models (LLMs). However, the research community still lacks an open, large-scale, high-quality corpus tailored to…

Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets,…

Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption…

Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…

Self-supervised learning has emerged as a powerful way to pre-train generalizable machine learning models on large amounts of unlabeled data. It is particularly compelling in the music domain, where obtaining labeled data is time-consuming,…

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive…

Symbolic music understanding, which refers to the understanding of music from the symbolic data (e.g., MIDI format, but not audio), covers many music applications such as genre classification, emotion classification, and music pieces…