SyMuPe: Affective and Controllable Symbolic Music Performance

• URL: http://arxiv.org/abs/2511.03425v1
• Date: Wed, 05 Nov 2025 12:42:08 GMT
• Title: SyMuPe: Affective and Controllable Symbolic Music Performance
• Abstract summary: We present SyMuPe, a novel framework for developing and training affective and controllable piano performance models.<n>Our flagship model, PianoFlow, uses conditional flow matching trained to solve diverse multi-mask performance inpainting tasks.<n>For emotion control, we present and analyze samples generated under different text conditioning scenarios.
• Score: 0.00746020873338928
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Emotions are fundamental to the creation and perception of music performances. However, achieving human-like expression and emotion through machine learning models for performance rendering remains a challenging task. In this work, we present SyMuPe, a novel framework for developing and training affective and controllable symbolic piano performance models. Our flagship model, PianoFlow, uses conditional flow matching trained to solve diverse multi-mask performance inpainting tasks. By design, it supports both unconditional generation and infilling of music performance features. For training, we use a curated, cleaned dataset of 2,968 hours of aligned musical scores and expressive MIDI performances. For text and emotion control, we integrate a piano performance emotion classifier and tune PianoFlow with the emotion-weighted Flan-T5 text embeddings provided as conditional inputs. Objective and subjective evaluations against transformer-based baselines and existing models show that PianoFlow not only outperforms other approaches, but also achieves performance quality comparable to that of human-recorded and transcribed MIDI samples. For emotion control, we present and analyze samples generated under different text conditioning scenarios. The developed model can be integrated into interactive applications, contributing to the creation of more accessible and engaging music performance systems.

Related papers

• Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control [66.46754271097555]
  We release a fully open-source system for long-form song generation with fine-grained style conditioning.<n>The dataset consists of 116k fully licensed synthetic songs with automatically generated lyrics and style descriptions.<n>We train Muse via single-stage supervised finetuning of a Qwen-based language model extended with discrete audio tokens.
  arXiv  Detail & Related papers  (2026-01-07T14:40:48Z)
• Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition [11.051812953517521]
  Music emotion recognition is a key task in symbolic music understanding.<n>Recent approaches have shown promising results by fine-tuning models to map musical semantics to emotional labels.<n>We propose a Mode-Guided Enhancement (MoGE) strategy that incorporates psychological insights on mode into the model.
  arXiv  Detail & Related papers  (2025-12-15T03:27:35Z)
• Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training [26.885642751756695]
  Pianist Transformer is a unified Musical Instrument Digital Interface (MIDI) data representation for learning the shared principles of musical structure and expression without explicit annotation.<n>It achieves strong objective metrics and human-level subjective ratings.<n>Overall, Pianist Transformer establishes a scalable path toward human-like performance synthesis in the music domain.
  arXiv  Detail & Related papers  (2025-12-02T11:13:29Z)
• Story2MIDI: Emotionally Aligned Music Generation from Text [38.36870481571071]
  We introduce Story2MIDI, a sequence-to-sequence Transformer-based model for generating emotion-aligned music from a given piece of text.<n>Our results indicate that our model effectively learns emotion-relevant features in music and incorporates them into its generation process.
  arXiv  Detail & Related papers  (2025-12-01T20:35:18Z)
• The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity [59.78509280246215]
  Aria-Duet is an interactive system facilitating a real-time musical duet between a human pianist and Aria, a state-of-the-art generative model.<n>We analyze the system's output from a musicological perspective, finding the model can maintain stylistic semantics and develop coherent phrasal ideas.
  arXiv  Detail & Related papers  (2025-11-03T15:26:01Z)
• Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries [1.1743167854433303]
  EMSYNC is a video-based symbolic music generation model that aligns music with a video's emotional content and temporal boundaries.<n>We introduce boundary offsets, a novel temporal conditioning mechanism that enables the model to anticipate and align musical chords with scene cuts.<n>In subjective listening tests, EMSYNC outperforms state-of-the-art models across all subjective metrics, for music theory-aware participants as well as the general listeners.
  arXiv  Detail & Related papers  (2025-02-14T13:32:59Z)
• MusicFlow: Cascaded Flow Matching for Text Guided Music Generation [53.63948108922333]
  MusicFlow is a cascaded text-to-music generation model based on flow matching. We leverage masked prediction as the training objective, enabling the model to generalize to other tasks such as music infilling and continuation.
  arXiv  Detail & Related papers  (2024-10-27T15:35:41Z)
• Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation [19.139752434303688]
  Managing the emotional aspect remains a challenge in automatic music generation. This paper explores the disentanglement of emotions in piano performance generation through a two-stage framework.
  arXiv  Detail & Related papers  (2024-07-30T16:29:28Z)
• Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis [15.670399197114012]
  We propose enhancing control of multi-instrument synthesis by conditioning a generative model on a specific performance and recording environment. Performance conditioning is a tool indicating the generative model to synthesize music with style and timbre of specific instruments taken from specific performances. Our prototype is evaluated using uncurated performances with diverse instrumentation and state-of-the-art FAD realism scores.
  arXiv  Detail & Related papers  (2023-09-21T17:44:57Z)
• Anticipatory Music Transformer [60.15347393822849]
  We introduce anticipation: a method for constructing a controllable generative model of a temporal point process. We focus on infilling control tasks, whereby the controls are a subset of the events themselves. We train anticipatory infilling models using the large and diverse Lakh MIDI music dataset.
  arXiv  Detail & Related papers  (2023-06-14T16:27:53Z)
• A Novel Multi-Task Learning Method for Symbolic Music Emotion Recognition [76.65908232134203]
  Symbolic Music Emotion Recognition(SMER) is to predict music emotion from symbolic data, such as MIDI and MusicXML. In this paper, we present a simple multi-task framework for SMER, which incorporates the emotion recognition task with other emotion-related auxiliary tasks.
  arXiv  Detail & Related papers  (2022-01-15T07:45:10Z)
• MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling [6.256118777336895]
  Musical expression requires control of both what notes are played, and how they are performed. We introduce MIDI-DDSP, a hierarchical model of musical instruments that enables both realistic neural audio synthesis and detailed user control. We demonstrate that this hierarchy can reconstruct high-fidelity audio, accurately predict performance attributes for a note sequence, independently manipulate the attributes of a given performance, and as a complete system, generate realistic audio from a novel note sequence.
  arXiv  Detail & Related papers  (2021-12-17T04:15:42Z)
• Music Gesture for Visual Sound Separation [121.36275456396075]
  "Music Gesture" is a keypoint-based structured representation to explicitly model the body and finger movements of musicians when they perform music. We first adopt a context-aware graph network to integrate visual semantic context with body dynamics, and then apply an audio-visual fusion model to associate body movements with the corresponding audio signals.
  arXiv  Detail & Related papers  (2020-04-20T17:53:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.