MusPy: A Toolkit for Symbolic Music Generation
Not on the map. Why?
Abstract (arXiv)
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 and model evaluation. In order to showcase its potential, we present statistical analysis of the eleven datasets currently supported by MusPy. Moreover, we conduct a cross-dataset generalizability experiment by training an autoregressive model on each dataset and measuring held-out likelihood on the others---a process which is made easier by MusPy's dataset management system. The results provide a map of domain overlap between various commonly used datasets and show that some datasets contain more representative cross-genre samples than others. Along with the dataset analysis, these results might serve as a guide for choosing datasets in future research. Source code and documentation are available at https://github.com/salu133445/muspy .
Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 8; 2023: 8; 2024: 10; 2025: 2; 2026: 5.
37 papers.
Sort:
By area:
- 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 174
- 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
- 2023Anticipatory Music Transformercited by 35
- 2022Multitrack Music Transformercited by 28
- 2022Video Background Music Generation: Dataset, Method and Evaluationcited by 28
- 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
- 2023miditok: A Python package for MIDI file tokenizationcited by 26
- 2021DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Modelscited by 20
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processingcited by 15
- 2022Deep Performer: Score-to-Audio Music Performance Synthesiscited by 12
- 2024Frechet Music Distance: A Metric For Generative Symbolic Music Evaluationcited by 12
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
25 more
- 2022Generating music with sentiment using Transformer-GANscited by 11
- 2023GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformerscited by 11
- 2021Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Musiccited by 5
- 2023ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal Productioncited by 4
- 2024The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videoscited by 4
- 2022A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectivescited by 3
- 2024Between the AI and Me: Analysing Listeners' Perspectives on AI- and Human-Composed Progressive Metal Musiccited by 3
- 2023An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generationcited by 2
- 2023From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generationcited by 2
- 2023MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotioncited by 2
- 2024A Survey of Music Generation in the Context of Interactioncited by 2
- 2025Time-Shifted Token Scheduling for Symbolic Music Generationcited by 2
- 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Stepscited by 2
- 2023An Order-Complexity Model for Aesthetic Quality Assessment of Symbolic Homophony Music Scorescited by 1
- 2024Evaluating Co-Creativity using Total Information Flowcited by 1
- 2024MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERTcited by 1
- 2024Prevailing Research Areas for Music AI in the Era of Foundation Modelscited by 1
- 2026ViTex: Visual Texture Control for Multi-Track Symbolic Music Generation via Discrete Diffusion Modelscited by 1
- 2026MusPyExpress: Extending MusPy with Enhanced Expression Text Supportcited by 1
- 2022Representation Learning for the Automatic Indexing of Sound Effects Librariescited by 0
- 2024Siamese Residual Neural Network for Musical Shape Evaluation in Piano Performance Assessmentcited by 0
- 2024MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic musiccited by 0
- 2025Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approachcited by 0
- 2026Can LLMs understand LilyPond? A benchmark for symbolic music generation and understandingcited by 0
- 2026ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generationcited by 0
- 2026MusPyExpress: Extending MusPy with Enhanced Expression Text Support21 Aug 2026
- 2026ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation14 Jul 2026
- 2026Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding7 Jun 2026
- 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps21 Apr 2026
- 2026ViTex: Visual Texture Control for Multi-Track Symbolic Music Generation via Discrete Diffusion Models2 Mar 2026
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach26 Sep 2025
- 2024Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation10 Dec 2024
- 2024MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic music27 Oct 2024
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing17 Sep 2024
- 2024Prevailing Research Areas for Music AI in the Era of Foundation Models14 Sep 2024
- 2024MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT2 Sep 2024
25 more
- 2024Between the AI and Me: Analysing Listeners' Perspectives on AI- and Human-Composed Progressive Metal Music31 Jul 2024
- 2024The NES Video-Music Database: A Dataset of Symbolic Video Game Music Paired with Gameplay Videos5 Apr 2024
- 2024A Survey of Music Generation in the Context of Interaction23 Feb 2024
- 2024Evaluating Co-Creativity using Total Information Flow9 Feb 2024
- 2024Siamese Residual Neural Network for Musical Shape Evaluation in Piano Performance Assessment4 Jan 2024
- 2023MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion16 Dec 2023
- 2023miditok: A Python package for MIDI file tokenization26 Oct 2023
- 2023ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal Production11 Jul 2023
- 2023Anticipatory Music Transformer14 Jun 2023
- 2023From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation18 Apr 2023
- 2023GTR-CTRL: Instrument and Genre Conditioning for Guitar-Focused Music Generation with Transformers10 Feb 2023
- 2023An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generation31 Jan 2023
- 2023An Order-Complexity Model for Aesthetic Quality Assessment of Symbolic Homophony Music Scores14 Jan 2023
- 2022Generating music with sentiment using Transformer-GANs21 Dec 2022
- 2022Video Background Music Generation: Dataset, Method and Evaluation21 Nov 2022
- 2022A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives25 Oct 2022
- 2022Representation Learning for the Automatic Indexing of Sound Effects Libraries18 Aug 2022
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search10 Aug 2022
- 2022Multitrack Music Transformer14 Jul 2022
- 2022Deep Performer: Score-to-Audio Music Performance Synthesis12 Feb 2022
- 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection2 Feb 2022
- 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data15 Dec 2021
- 2021DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Models30 Jul 2021
- 2021Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music13 Jul 2021
- 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs7 Jan 2021
- 2022HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detectioncited by 174
- 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
- 2023Anticipatory Music Transformercited by 35
- 2022Multitrack Music Transformercited by 28
- 2022Video Background Music Generation: Dataset, Method and Evaluationcited by 28
- 2021Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Datacited by 27
- 2023miditok: A Python package for MIDI file tokenizationcited by 26
- 2021DadaGP: A Dataset of Tokenized GuitarPro Songs for Sequence Modelscited by 20
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processingcited by 15
- 2022Deep Performer: Score-to-Audio Music Performance Synthesiscited by 12
- 2024Frechet Music Distance: A Metric For Generative Symbolic Music Evaluationcited by 12
- 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
12 most cited of 36 All 36 (JSON)
- 2026MusPyExpress: Extending MusPy with Enhanced Expression Text Support21 Aug 2026
- 2026ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation14 Jul 2026
- 2026Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding7 Jun 2026
- 2026BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps21 Apr 2026
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach26 Sep 2025
- 2024Frechet Music Distance: A Metric For Generative Symbolic Music Evaluation10 Dec 2024
- 2024MidiTok Visualizer: a tool for visualization and analysis of tokenized MIDI symbolic music27 Oct 2024
- 2024PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing17 Sep 2024
- 2024Prevailing Research Areas for Music AI in the Era of Foundation Models14 Sep 2024
- 2024MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT2 Sep 2024
- 2024Between the AI and Me: Analysing Listeners' Perspectives on AI- and Human-Composed Progressive Metal Music31 Jul 2024
12 newest of 36 All 36 (JSON)