English
Related papers

Related papers: miditok: A Python package for MIDI file tokenizati…

200 papers

We present the API for MUSICNTWRK, a python library for pitch class set and rhythmic sequences classification and manipulation, the generation of networks in generalized music and sound spaces, deep learning algorithms for timbre…

Sound · Computer Science 2020-07-22 Marco Buongiorno Nardelli

Large Audio Language Models (LALMs) have emerged with strong performance across diverse audio understanding tasks and can be further enhanced by neural audio codecs. Transitioning from multi-layer residual vector quantizers to a…

Sound · Computer Science 2025-12-05 Jingyi Li , Zhiyuan Zhao , Zhisheng Zhang , Yunfei Liu , Lijian Lin , Ye Zhu , Jiahao Wu , Qiuqiang Kong , Yu Li

A short overview demystifying the midi audio format is presented. The goal is to explain the file structure and how the instructions are used to produce a music signal, both in the case of monophonic signals as for polyphonic signals.

Sound · Computer Science 2018-01-24 H. M. de Oliveira , R. C. de Oliveira

This paper introduces text2midi, an end-to-end model to generate MIDI files from textual descriptions. Leveraging the growing popularity of multimodal generative approaches, text2midi capitalizes on the extensive availability of textual…

Sound · Computer Science 2025-06-18 Keshav Bhandari , Abhinaba Roy , Kyra Wang , Geeta Puri , Simon Colton , Dorien Herremans

Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Anni Tang , Tianyu He , Junliang Guo , Xinle Cheng , Li Song , Jiang Bian

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)…

Sound · Computer Science 2021-12-02 Masahiro Suzuki

Representing symbolic music with compound tokens, where each token consists of several different sub-tokens representing a distinct musical feature or attribute, offers the advantage of reducing sequence length. While previous research has…

Sound · Computer Science 2026-03-17 HaeJun Yoo , Hao-Wen Dong , Jongmin Jung , Dasaem Jeong

Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under…

Machine Learning · Computer Science 2026-02-04 Xiaoce Wang , Guibin Zhang , Junzhe Li , Jinzhe Tu , Chun Li , Ming Li

In this paper, we introduce the MIDI Degradation Toolkit (MDTK), containing functions which take as input a musical excerpt (a set of notes with pitch, onset time, and duration), and return a "degraded" version of that excerpt with some…

Sound · Computer Science 2020-10-02 Andrew McLeod , James Owers , Kazuyoshi Yoshii

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,…

Sound · Computer Science 2024-07-26 Léo Géré , Philippe Rigaux , Nicolas Audebert

In this paper, we present MusPy, an open source Python library for symbolic music generation. MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing…

Sound · Computer Science 2020-08-06 Hao-Wen Dong , Ke Chen , Julian McAuley , Taylor Berg-Kirkpatrick

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yiwei Guo , Shaobin Zhuang , Zhipeng Huang , Canmiao Fu , Chen Li , Jing Lyu , Yali Wang

Modelling human perception of musical similarity is critical for the evaluation of generative music systems, musicological research, and many Music Information Retrieval tasks. Although human similarity judgments are the gold standard,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-29 Jeff Ens , Philippe Pasquier

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…

Sound · Computer Science 2025-09-30 Junyan Jiang , Daniel Chin , Liwei Lin , Xuanjie Liu , Gus Xia

NLTK, the Natural Language Toolkit, is a suite of open source program modules, tutorials and problem sets, providing ready-to-use computational linguistics courseware. NLTK covers symbolic and statistical natural language processing, and is…

Computation and Language · Computer Science 2007-05-23 Edward Loper , Steven Bird

Symbolic music is widely used in various deep learning tasks, including generation, transcription, synthesis, and Music Information Retrieval (MIR). It is mostly employed with discrete models like Transformers, which require music to be…

Sound · Computer Science 2023-10-13 Nathan Fradet , Nicolas Gutowski , Fabien Chhel , Jean-Pierre Briot

Music transcription plays a pivotal role in Music Information Retrieval (MIR), particularly for stringed instruments like the guitar, where symbolic music notations such as MIDI lack crucial playability information. This contribution…

Sound · Computer Science 2025-06-18 Anna Hamberger , Sebastian Murgul , Jochen Schmidt , Michael Heizmann

Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and inference, as well as competitive performance across diverse…

Foundation models trained on patient electronic health records (EHRs) require tokenizing medical data into sequences of discrete vocabulary items. Existing tokenizers treat medical codes from EHRs as isolated textual tokens. However, each…

Computation and Language · Computer Science 2025-07-01 Xiaorui Su , Shvat Messica , Yepeng Huang , Ruth Johnson , Lukas Fesser , Shanghua Gao , Faryad Sahneh , Marinka Zitnik

This paper presents a web application for visualizing the tonality of a piece of music -- the organization of its chords and scales -- at a high level of abstraction and with coordinated playback. The application applies the discrete…

Sound · Computer Science 2022-03-25 Daniel Harasim , Giovanni Affatato , Fabian C. Moss