MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
Not on the map. Why?
Abstract (arXiv)
We propose the Multi-Track Music Machine (MMM), a generative system based on the Transformer architecture that is capable of generating multi-track music. In contrast to previous work, which represents musical material as a single time-ordered sequence, where the musical events corresponding to different tracks are interleaved, we create a time-ordered sequence of musical events for each track and concatenate several tracks into a single sequence. This takes advantage of the Transformer's attention-mechanism, which can adeptly handle long-term dependencies. We explore how various representations can offer the user a high degree of control at generation time, providing an interactive demo that accommodates track-level and bar-level inpainting, and offers control over track instrumentation and note density.
Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 8; 2023: 9; 2024: 14; 2025: 10; 2026: 3.
48 papers.
Sort:
By area:
- 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
- 2023MuseCoco: Generating Symbolic Music from Textcited by 50
- 2022Symphony Generation with Permutation Invariant Language Modelcited by 35
- 2024Foundation Models for Music: A Surveycited by 34
- 2022Multitrack Music Transformercited by 28
- 2023miditok: A Python package for MIDI file tokenizationcited by 26
- 2022MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Controlcited by 17
- 2023JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generationcited by 17
- 2023GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Frameworkcited by 13
- 2021Music Composition with Deep Learning: A Reviewcited by 12
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
- 2023Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infillingcited by 9
36 more
- 2022ComMU: Dataset for Combinatorial Music Generationcited by 8
- 2021Score Transformer: Generating Musical Score from Note-level Representationcited by 7
- 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotationscited by 7
- 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detectioncited by 7
- 2023Impact of time and note duration tokenizations on deep learning symbolic music modelingcited by 6
- 2021Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Musiccited by 5
- 2022Subjective Evaluation of Deep Learning Models for Symbolic Music Compositioncited by 5
- 2024A Survey of Deep Learning Audio Generation Methodscited by 5
- 2024Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Controlcited by 5
- 2024Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Modelcited by 5
- 2024PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variationscited by 4
- 2025Evaluating Human-AI Interaction via Usability, User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Compositioncited by 4
- 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributescited by 4
- 2022A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectivescited by 3
- 2023Symbolic Music Structure Analysis with Graph Representations and Changepoint Detection Methodscited by 3
- 2024Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenizationcited by 3
- 2025Exploring the Needs of Practising Musicians in Co-Creative AI Through Co-Designcited by 3
- 2024A Survey of Music Generation in the Context of Interactioncited by 2
- 2024BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Featurescited by 2
- 2025Time-Shifted Token Scheduling for Symbolic Music Generationcited by 2
- 2026Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSPcited by 2
- 2026SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeletoncited by 2
- 2022FIGARO: Generating Symbolic Music with Fine-Grained Artistic Controlcited by 1
- 2024Evaluating Co-Creativity using Total Information Flowcited by 1
- 2024Music Proofreading with RefinPaint: Where and How to Modify Compositions given Contextcited by 1
- 2024MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERTcited by 1
- 2024SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Trainingcited by 1
- 2025Calliope: An Online Generative Music System for Symbolic Multi-Track Compositioncited by 1
- 2025Adaptable Symbolic Music Infilling with MIDI-RWKVcited by 1
- 2025On the de-duplication of the Lakh MIDI datasetcited by 1
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understandingcited by 1
- 2023Exploring Softly Masked Language Modelling for Controllable Symbolic Music Generationcited by 0
- 2023JAMMIN-GPT: Text-based Improvisation using LLMs in Ableton Livecited by 0
- 2024Notochord: a Flexible Probabilistic Model for Real-Time MIDI Performancecited by 0
- 2025Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcriptioncited by 0
- 2026Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generationcited by 0
- 2026Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation6 May 2026
- 2026SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton28 Apr 2026
- 2026Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSP8 Apr 2026
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding18 Oct 2025
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025On the de-duplication of the Lakh MIDI dataset20 Sep 2025
- 2025Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription11 Aug 2025
- 2025Adaptable Symbolic Music Infilling with MIDI-RWKV16 Jun 2025
- 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes21 May 2025
- 2025Evaluating Human-AI Interaction via Usability, User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Composition18 Apr 2025
- 2025Calliope: An Online Generative Music System for Symbolic Multi-Track Composition18 Apr 2025
- 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detection24 Feb 2025
36 more
- 2025Exploring the Needs of Practising Musicians in Co-Creative AI Through Co-Design13 Feb 2025
- 2024SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training24 Dec 2024
- 2024PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations2 Oct 2024
- 2024Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Model4 Sep 2024
- 2024MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT2 Sep 2024
- 2024Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization27 Aug 2024
- 2024Foundation Models for Music: A Survey26 Aug 2024
- 2024Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Control19 Jul 2024
- 2024BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features15 Jul 2024
- 2024Music Proofreading with RefinPaint: Where and How to Modify Compositions given Context12 Jul 2024
- 2024A Survey of Deep Learning Audio Generation Methods31 May 2024
- 2024Notochord: a Flexible Probabilistic Model for Real-Time MIDI Performance18 Mar 2024
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey27 Feb 2024
- 2024A Survey of Music Generation in the Context of Interaction23 Feb 2024
- 2024Evaluating Co-Creativity using Total Information Flow9 Feb 2024
- 2023JAMMIN-GPT: Text-based Improvisation using LLMs in Ableton Live6 Dec 2023
- 2023JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation29 Oct 2023
- 2023miditok: A Python package for MIDI file tokenization26 Oct 2023
- 2023Impact of time and note duration tokenizations on deep learning symbolic music modeling12 Oct 2023
- 2023MuseCoco: Generating Symbolic Music from Text31 May 2023
- 2023GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Framework18 May 2023
- 2023Exploring Softly Masked Language Modelling for Controllable Symbolic Music Generation5 May 2023
- 2023Symbolic Music Structure Analysis with Graph Representations and Changepoint Detection Methods24 Mar 2023
- 2023Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling29 Jan 2023
- 2022ComMU: Dataset for Combinatorial Music Generation17 Nov 2022
- 2022YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations14 Nov 2022
- 2022A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives25 Oct 2022
- 2022Multitrack Music Transformer14 Jul 2022
- 2022Symphony Generation with Permutation Invariant Language Model10 May 2022
- 2022Subjective Evaluation of Deep Learning Models for Symbolic Music Composition28 Mar 2022
- 2022MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Control11 Feb 2022
- 2022FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control26 Jan 2022
- 2021Score Transformer: Generating Musical Score from Note-level Representation1 Dec 2021
- 2021Music Composition with Deep Learning: A Review27 Aug 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
- 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
- 2023MuseCoco: Generating Symbolic Music from Textcited by 50
- 2022Symphony Generation with Permutation Invariant Language Modelcited by 35
- 2022Multitrack Music Transformercited by 28
- 2023miditok: A Python package for MIDI file tokenizationcited by 26
- 2022MusIAC: An extensible generative framework for Music Infilling Applications with multi-level Controlcited by 17
- 2023JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generationcited by 17
- 2023GETMusic: Generating Any Music Tracks with a Unified Representation and Diffusion Frameworkcited by 13
- 2021Music Composition with Deep Learning: A Reviewcited by 12
- 2024Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Surveycited by 10
- 2023Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infillingcited by 9
- 2022ComMU: Dataset for Combinatorial Music Generationcited by 8
12 most cited of 45 All 45 (JSON)
- 2026Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation6 May 2026
- 2026SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton28 Apr 2026
- 2025MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding18 Oct 2025
- 2025Time-Shifted Token Scheduling for Symbolic Music Generation28 Sep 2025
- 2025On the de-duplication of the Lakh MIDI dataset20 Sep 2025
- 2025Exploring Procedural Data Generation for Automatic Acoustic Guitar Fingerpicking Transcription11 Aug 2025
- 2025Adaptable Symbolic Music Infilling with MIDI-RWKV16 Jun 2025
- 2025Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes21 May 2025
- 2025Evaluating Human-AI Interaction via Usability, User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Composition18 Apr 2025
- 2025Calliope: An Online Generative Music System for Symbolic Multi-Track Composition18 Apr 2025
- 2025The GigaMIDI Dataset with Features for Expressive Music Performance Detection24 Feb 2025
- 2025Exploring the Needs of Practising Musicians in Co-Creative AI Through Co-Design13 Feb 2025
12 newest of 45 All 45 (JSON)