Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jeyaraj, Rathinaraja, Subramanian, Barathi, Gangadharan, Kapilya, Paul, Anand
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913066449371136
author Jeyaraj, Rathinaraja
Subramanian, Barathi
Gangadharan, Kapilya
Paul, Anand
author_facet Jeyaraj, Rathinaraja
Subramanian, Barathi
Gangadharan, Kapilya
Paul, Anand
contents Gesture-driven music generation is an emerging human-computer interaction paradigm for touch-free and expressive musical interaction. However, many existing approaches treat the task as isolated gesture classification or map gestures to symbolic outputs such as MIDI followed by a separate rendering stage, which limits temporal continuity and real-time responsiveness. This work presents Gesture2Music, a low-latency streaming framework for continuous gesture-driven music generation from live webcam feed. The system processes sequences of body and hand landmarks and uses a causal temporal convolutional network (TCN) to predict note-level musical control events, including pitch, octave, onset, sustain, amplitude, and activity state. Because available gesture-note datasets typically contain only isolated single-note recordings rather than continuous performance sequences, a synthetic stream generation strategy is introduced to construct continuous gesture streams by concatenating single-note clips and deriving heuristic temporal event labels. Temporal consistency and spectral proxy losses are further used to reduce prediction jitter and encourage audio-consistent outputs. During inference, predicted musical events are rendered into continuous music using predefined note samples with rhythmic quantization and scale-constrained filtering for improved musical stability. Experiments on a custom gesture-to-music dataset with 21 gesture-note classes spanning seven tones across three pitch levels demonstrate stable real-time performance, low inference latency of 30\,ms, and improved temporal continuity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation
Jeyaraj, Rathinaraja
Subramanian, Barathi
Gangadharan, Kapilya
Paul, Anand
Multimedia
Sound
Gesture-driven music generation is an emerging human-computer interaction paradigm for touch-free and expressive musical interaction. However, many existing approaches treat the task as isolated gesture classification or map gestures to symbolic outputs such as MIDI followed by a separate rendering stage, which limits temporal continuity and real-time responsiveness. This work presents Gesture2Music, a low-latency streaming framework for continuous gesture-driven music generation from live webcam feed. The system processes sequences of body and hand landmarks and uses a causal temporal convolutional network (TCN) to predict note-level musical control events, including pitch, octave, onset, sustain, amplitude, and activity state. Because available gesture-note datasets typically contain only isolated single-note recordings rather than continuous performance sequences, a synthetic stream generation strategy is introduced to construct continuous gesture streams by concatenating single-note clips and deriving heuristic temporal event labels. Temporal consistency and spectral proxy losses are further used to reduce prediction jitter and encourage audio-consistent outputs. During inference, predicted musical events are rendered into continuous music using predefined note samples with rhythmic quantization and scale-constrained filtering for improved musical stability. Experiments on a custom gesture-to-music dataset with 21 gesture-note classes spanning seven tones across three pitch levels demonstrate stable real-time performance, low inference latency of 30\,ms, and improved temporal continuity.
title Gesture2Music: A Low-Latency Real-Time Framework for Continuous Gesture-Driven Music Generation
topic Multimedia
Sound
url https://arxiv.org/abs/2511.00793