Predicting Sex and Stroke Success -- Computer-aided Player Grunt Analysis in Tennis Matches

TL;DR

This study introduces SCORE!, a new dataset of tennis player grunts from YouTube, and demonstrates that machine learning models can predict player sex and stroke success from vocal cues with high accuracy.

Contribution

The paper presents a novel dataset and evaluates multiple acoustic features and machine learning models for predicting sex and stroke success from tennis grunts.

Findings

Spectrograms with CNN-RNN achieve 84.0% UAR for sex prediction.

Models predict stroke success with 60.3% UAR using vocal cues.

Training on specific genders yields comparable accuracy.

Abstract

Professional athletes increasingly use automated analysis of meta- and signal data to improve their training and game performance. As in other related human-to-human research fields, signal data, in particular, contain important performance- and mood-specific indicators for automated analysis. In this paper, we introduce the novel data set SCORE! to investigate the performance of several features and machine learning paradigms in the prediction of the sex and immediate stroke success in tennis matches, based only on vocal expression through players' grunts. The data was gathered from YouTube, labelled under the exact same definition, and the audio processed for modelling. We extract several widely used basic, expert-knowledge, and deep acoustic features of the audio samples and evaluate their effectiveness in combination with various machine learning approaches. In a binary setting, the best system, using spectrograms and a Convolutional Recurrent Neural Network, achieves an unweighted average recall (UAR) of 84.0 % for the player sex prediction task, and 60.3 % predicting stroke success, based only on acoustic cues in players' grunts of both sexes. Further, we achieve a UAR of 58.3 %, and 61.3 %, when the models are exclusively trained on female or male grunts, respectively.