Content-based Recommendations for Radio Stations with Deep Learned Audio Fingerprints

TL;DR

This paper introduces a novel audio fingerprinting method using deep autoencoders to improve radio station recommendations based on content, addressing limitations of metadata and user data reliance.

Contribution

It presents a new pipeline for generating audio-based radio station fingerprints with deep learning, enhancing content characterization and recommendation accuracy.

Findings

Fingerprints effectively characterize radio station audio content

Proposed system improves recommendation relevance

Open source platform supports small and medium businesses

Abstract

The world of linear radio broadcasting is characterized by a wide variety of stations and played content. That is why finding stations playing the preferred content is a tough task for a potential listener, especially due to the overwhelming number of offered choices. Here, recommender systems usually step in but existing content-based approaches rely on metadata and thus are constrained by the available data quality. Other approaches leverage user behavior data and thus do not exploit any domain-specific knowledge and are furthermore disadvantageous regarding privacy concerns. Therefore, we propose a new pipeline for the generation of audio-based radio station fingerprints relying on audio stream crawling and a Deep Autoencoder. We show that the proposed fingerprints are especially useful for characterizing radio stations by their audio content and thus are an excellent representation for meaningful and reliable radio station recommendations. Furthermore, the proposed modules are part of the HRADIO Communication Platform, which enables hybrid radio features to radio stations. It is released with a flexible open source license and enables especially small- and medium-sized businesses, to provide customized and high quality radio services to potential listeners.