中文
相关论文

相关论文: The Power of Fragmentation: A Hierarchical Transfo…

200 篇论文

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a…

声音 · 计算机科学 2024-02-29 Manvi Agarwal , Changhong Wang , Gaël Richard

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

声音 · 计算机科学 2024-03-14 Keshav Bhandari , Simon Colton

This paper describes a data-driven framework to parse musical sequences into dependency trees, which are hierarchical structures used in music cognition research and music analysis. The parsing involves two steps. First, the input sequence…

声音 · 计算机科学 2023-06-30 Francesco Foscarin , Daniel Harasim , Gerhard Widmer

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…

声音 · 计算机科学 2022-10-07 Chih-Pin Tan , Alvin W. Y. Su , Yi-Hsuan Yang

Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by…

声音 · 计算机科学 2023-05-29 Xipin Wei , Junhui Chen , Zirui Zheng , Li Guo , Lantian Li , Dong Wang

Recently, symbolic music generation has become a focus of numerous deep learning research. Structure as an important part of music, contributes to improving the quality of music, and an increasing number of works start to study the…

声音 · 计算机科学 2024-10-16 Yishan Lv , Jing Luo , Boyuan Ju , Xinyu Yang

AI-based music generation has made significant progress in recent years. However, generating symbolic music that is both long-structured and expressive remains a significant challenge. In this paper, we propose PerceiverS (Segmentation and…

人工智能 · 计算机科学 2025-09-23 Yungang Yi , Weihua Li , Matthew Kuo , Quan Bai

At present, neural network-based models, including transformers, struggle to generate memorable and readily comprehensible music from unified and repetitive musical material due to a lack of understanding of musical structure. Consequently,…

声音 · 计算机科学 2026-01-21 Shangxuan Luo , Joshua Reiss

Music contains hierarchical structures beyond beats and measures. While hierarchical structure annotations are helpful for music information retrieval and computer musicology, such annotations are scarce in current digital music databases.…

声音 · 计算机科学 2022-09-22 Junyan Jiang , Daniel Chin , Yixiao Zhang , Gus Xia

Recent deep music generation studies have put much emphasis on long-term generation with structures. However, we are yet to see high-quality, well-structured whole-song generation. In this paper, we make the first attempt to model a full…

声音 · 计算机科学 2024-05-17 Ziyu Wang , Lejun Min , Gus Xia

The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Subsequently, the…

声音 · 计算机科学 2023-12-18 Jinhao Tian , Zuchao Li , Jiajia Li , Ping Wang

Structure perception is a fundamental aspect of music cognition in humans. Historically, the hierarchical organization of music into structures served as a narrative device for conveying meaning, creating expectancy, and evoking emotions in…

声音 · 计算机科学 2023-03-28 Nicolas Lazzari , Andrea Poltronieri , Valentina Presutti

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…

声音 · 计算机科学 2020-07-01 Kristy Choi , Curtis Hawthorne , Ian Simon , Monica Dinculescu , Jesse Engel

In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores. Thus far, sequence models have yielded fruitful results with note-level (MIDI-equivalent)…

声音 · 计算机科学 2021-12-02 Masahiro Suzuki

Many music AI models learn a map between music content and human-defined labels. However, many annotations, such as chords, can be naturally expressed within the music modality itself, e.g., as sequences of symbolic notes. This observation…

声音 · 计算机科学 2025-09-30 Junyan Jiang , Daniel Chin , Liwei Lin , Xuanjie Liu , Gus Xia

Compositional structures between parts and objects are inherent in natural scenes. Modeling such compositional hierarchies via unsupervised learning can bring various benefits such as interpretability and transferability, which are…

机器学习 · 计算机科学 2019-10-22 Fei Deng , Zhuo Zhi , Sungjin Ahn

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…

Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a…

计算机视觉与模式识别 · 计算机科学 2014-08-26 Sanja Fidler , Marko Boben , Ales Leonardis

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…

声音 · 计算机科学 2023-07-28 Emanuele Cosenza , Andrea Valenti , Davide Bacciu

Deep learning models have become a critical tool for analysis and classification of musical data. These models operate either on the audio signal, e.g. waveform or spectrogram, or on a symbolic representation, such as MIDI. In the latter,…

声音 · 计算机科学 2024-07-26 Léo Géré , Philippe Rigaux , Nicolas Audebert
‹ 上一页 1 2 3 10 下一页 ›