Surfboard: Audio Feature Extraction for Modern Machine Learning

TL;DR

Surfboard is an open-source Python library designed for efficient audio feature extraction, specifically tailored for medical applications like Parkinson's disease classification, and supports integration with modern machine learning workflows.

Contribution

It introduces a new, user-friendly audio feature extraction library optimized for clinical research, addressing limitations of existing tools and supporting large-scale processing.

Findings

Successfully applied to Parkinson's classification using mPower dataset

Highlights common pitfalls in existing audio research methods

Facilitates future clinical audio research with open-source tools

Abstract

We introduce Surfboard, an open-source Python library for extracting audio features with application to the medical domain. Surfboard is written with the aim of addressing pain points of existing libraries and facilitating joint use with modern machine learning frameworks. The package can be accessed both programmatically in Python and via its command line interface, allowing it to be easily integrated within machine learning workflows. It builds on state-of-the-art audio analysis packages and offers multiprocessing support for processing large workloads. We review similar frameworks and describe Surfboard's architecture, including the clinical motivation for its features. Using the mPower dataset, we illustrate Surfboard's application to a Parkinson's disease classification task, highlighting common pitfalls in existing research. The source code is opened up to the research community to facilitate future audio research in the clinical domain.