Sound-Based Spin Estimation in Table Tennis: Dataset and Real-Time Classification Pipeline

TL;DR

This paper introduces a real-time audio-based system for detecting bounces, classifying contact surfaces, and estimating spin in table tennis, using a novel dataset and neural network models to enhance robotic and coaching applications.

Contribution

It presents a novel dataset and a real-time classification pipeline for spin and contact surface detection solely from audio in table tennis.

Findings

High accuracy in bounce detection and surface classification.

Reliable spin detection from audio signals.

Real-time processing capability demonstrated.

Abstract

Sound can complement vision in ball sports by providing subtle cues about contact dynamics. In table tennis, the brief, high-frequency sounds produced during racket-ball impacts carry information about the racket type, the surface contacted, and whether spin was applied. We address three key problems in this domain: (1) precise bounce detection with millisecond-level temporal accuracy, (2) classification of bounce surface (e.g., racket, table, floor), and (3) spin detection from audio alone. To this end, we propose a real-time-capable pipeline that combines energy-based peak detection with convolutional neural networks trained on a novel dataset of 3,396 bounce samples recorded across 10 racket configurations. The system achieves accurate and low-latency detection of bounces, and reliably classifies both the surface of contact and whether spin was applied. This audio-based approach opens up new possibilities for spin estimation in robotic systems and for real-time feedback in coaching tools. We publicly release both the dataset and code to support further research.